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

    Neuronpedia

    INDEX
    Explanations

    titles or descriptions related to individuals and their professions

    oai_token-act-pair · gpt-3.5-turbo

    words related to military and veteran status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adders
    -0.75
    ouls
    -0.70
    sers
    -0.70
    okers
    -0.66
    Score
    -0.64
    Xi
    -0.64
    apo
    -0.63
    acters
    -0.63
    Size
    -0.63
    erity
    -0.62
    POSITIVE LOGITS
     specializing
    1.06
     extraord
    0.98
    Joined
    0.90
     whose
    0.90
     who
    0.74
     studying
    0.74
     testified
    0.74
    ess
    0.73
     educator
    0.71
     adjunct
    0.71
    Act Density 0.265%

    No Known Activations