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

    Neuronpedia

    INDEX
    Explanations

    instances of complex sentences discussing conditions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardu
    -0.17
    atatype
    -0.15
    itol
    -0.15
    анÑģ
    -0.15
    _audit
    -0.14
    addAction
    -0.14
    yles
    -0.14
     Lauderdale
    -0.14
    ĵåIJį
    -0.14
     Kush
    -0.14
    POSITIVE LOGITS
    _drop
    0.14
    566
    0.14
    ett
    0.14
    odzi
    0.14
    illing
    0.13
    fr
    0.13
     signature
    0.13
    ira
    0.13
    »
    0.13
    /
    0.13
    Act Density 0.228%

    No Known Activations