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

    Neuronpedia

    INDEX
    Explanations

    words related to family relationships, particularly step-family relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to age and school levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.83
     Voy
    -0.72
     Canaver
    -0.67
    thora
    -0.67
     Tune
    -0.66
     Interstellar
    -0.65
     Sequence
    -0.65
     Smile
    -0.64
     Conquest
    -0.63
     Doomsday
    -0.63
    POSITIVE LOGITS
    arians
    0.97
    member
    0.91
     staffer
    0.89
     member
    0.86
    entle
    0.85
     officer
    0.85
    blers
    0.84
    arers
    0.84
    league
    0.83
    enders
    0.83
    Act Density 0.882%

    No Known Activations