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

    Neuronpedia

    INDEX
    Explanations

    strongly expressed opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Procedure
    -0.75
     Journals
    -0.73
     Thumbnails
    -0.72
    eon
    -0.72
    adr
    -0.71
    arters
    -0.70
    OTOS
    -0.69
     Settlement
    -0.69
    eria
    -0.68
     Gallery
    -0.68
    POSITIVE LOGITS
     enough
    0.96
     strongly
    0.86
     discouraged
    0.85
     encouraged
    0.83
     correlated
    0.82
     typed
    0.81
     differentiated
    0.79
     disagree
    0.79
     appreciated
    0.76
     advised
    0.75
    Act Density 0.009%

    No Known Activations