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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relational or causal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.05
     purpoſe
    -1.03
     ſtate
    -1.01
     myſelf
    -0.99
     houſe
    -0.97
     ſche
    -0.95
     pleaſure
    -0.91
     coö
    -0.89
     Anſ
    -0.87
     Houſe
    -0.86
    POSITIVE LOGITS
     the
    1.39
     a
    0.99
     an
    0.98
    <>();
    0.75
     their
    0.72
     them
    0.72
     these
    0.72
     some
    0.71
    :
    0.71
     several
    0.68
    Act Density 1.448%

    No Known Activations