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

    Neuronpedia

    INDEX
    Explanations

    specific references to locations and situational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Getter
    -0.17
    ofile
    -0.17
    ooke
    -0.16
     Pir
    -0.15
    icros
    -0.14
    Pixels
    -0.14
    ÅĻez
    -0.14
     Fade
    -0.13
    endencies
    -0.13
    yyyy
    -0.13
    POSITIVE LOGITS
     nor
    0.27
     anymore
    0.27
     unless
    0.24
    nor
    0.23
    unless
    0.21
     Nor
    0.20
     sino
    0.18
    Nor
    0.17
     NOR
    0.17
     Unless
    0.16
    Act Density 0.396%

    No Known Activations