Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns, particularly when expressing personal opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first-person pronouns and statements of personal opinion or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first person positive opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.60
    ViewImports
    -0.59
     Cæsar
    -0.58
     ILogger
    -0.56
     ſtate
    -0.56
     himſelf
    -0.55
    __()
    -0.53
     ſy
    -0.53
     Manche
    -0.51
     prediction
    -0.51
    POSITIVE LOGITS
     appreciated
    0.72
     applaud
    0.69
     appreciate
    0.66
    Impressive
    0.65
     nice
    0.65
     particularly
    0.64
     applauded
    0.63
     impressed
    0.63
     impressive
    0.63
     Particularly
    0.62
    Act Density 0.076%

    No Known Activations