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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix "-ager" and similar occupational or role-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erest
    -0.71
    orses
    -0.63
    ccording
    -0.62
    eny
    -0.60
     haste
    -0.59
    buquerque
    -0.59
    utes
    -0.58
    edit
    -0.58
    ers
    -0.58
    aepernick
    -0.56
    POSITIVE LOGITS
    jee
    1.18
    geist
    1.07
    lein
    1.03
    bilt
    1.02
    idge
    0.99
    lite
    0.96
    clips
    0.96
    stein
    0.88
    loo
    0.88
    dal
    0.87
    Act Density 0.187%

    No Known Activations