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

    Neuronpedia

    INDEX
    Explanations

    questions and statements of uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.31
     myſelf
    -1.19
     ſche
    -1.15
    ſelves
    -1.14
     Majefty
    -1.12
     itſelf
    -1.08
     themſelves
    -1.06
     ſeveral
    -1.06
     ſever
    -1.03
    ſelf
    -1.03
    POSITIVE LOGITS
     it
    1.19
     the
    1.01
     a
    0.92
     this
    0.84
     he
    0.84
     happens
    0.79
     we
    0.78
     kind
    0.75
     their
    0.74
     they
    0.73
    Act Density 0.114%

    No Known Activations