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

    Neuronpedia

    INDEX
    Explanations

    numerical data and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;
    -0.52
    .
    -0.50
     feeling
    -0.48
    :
    -0.46
    ?
    -0.45
    ,
    -0.44
    ↵↵
    -0.44
     felt
    -0.44
    -
    -0.43
     .
    -0.43
    POSITIVE LOGITS
     Efq
    0.94
     autorytatywna
    0.83
     Phry
    0.80
    ſelf
    0.78
     himſelf
    0.75
     themſelves
    0.74
     myſelf
    0.74
     iſt
    0.71
    ſelves
    0.71
     Shakspeare
    0.70
    Act Density 0.137%

    No Known Activations