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

    Neuronpedia

    INDEX
    Explanations

    references to scrolling and navigation within a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    __":
    -1.07
    aarrggbb
    -1.05
    __':
    -1.01
    ]--;
    -0.86
    __":
    -0.85
     Efq
    -0.84
     myſelf
    -0.84
    __':
    -0.81
     }}"></
    -0.81
    EDEFAULT
    -0.79
    POSITIVE LOGITS
    ,
    0.60
     for
    0.60
     to
    0.57
    ...
    0.47
    …
    0.47
     –
    0.46
     
    0.45
    .
    0.45
    /
    0.44
    )
    0.44
    Act Density 0.030%

    No Known Activations