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

    Neuronpedia

    INDEX
    Explanations

    mentions of first-time events or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "first."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.89
     Canaver
    -0.82
     oneself
    -0.76
     Guan
    -0.74
    rish
    -0.74
    halla
    -0.70
     Mahm
    -0.70
     Mous
    -0.70
    arth
    -0.70
     Committees
    -0.70
    POSITIVE LOGITS
     foray
    0.98
     outing
    0.89
     career
    0.83
     cousin
    0.82
     incarnation
    0.79
     comeback
    0.78
     birthday
    0.78
     counterparts
    0.77
     mortal
    0.77
     adversary
    0.75
    Act Density 0.239%

    No Known Activations