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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that begin with the word "Nothing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     something
    -0.15
    enu
    -0.14
    mont
    -0.14
    mps
    -0.14
     Thornton
    -0.14
    antine
    -0.13
    azor
    -0.13
     ExecutionContext
    -0.13
    aic
    -0.13
    uda
    -0.13
    POSITIVE LOGITS
     else
    0.30
    ness
    0.27
    else
    0.23
     wrong
    0.22
    wrong
    0.22
    Else
    0.21
    /no
    0.21
    Wrong
    0.20
    _else
    0.20
    burger
    0.20
    Act Density 0.033%

    No Known Activations