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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups with specific roles or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifie
    -0.15
    ially
    -0.15
    enen
    -0.15
    inya
    -0.14
    kk
    -0.14
    fil
    -0.13
    ifiable
    -0.13
    ppers
    -0.13
    zew
    -0.13
    isms
    -0.13
    POSITIVE LOGITS
     own
    0.27
    soever
    0.24
    oping
    0.21
    own
    0.21
     whose
    0.19
    whose
    0.18
     Own
    0.18
    upon
    0.17
    commended
    0.17
    _own
    0.16
    Act Density 0.017%

    No Known Activations