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

    Neuronpedia

    INDEX
    Explanations

    numerical values and relevant formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;
    -0.57
    .
    -0.56
    matchCondition
    -0.55
     Vikipedi
    -0.52
    <eos>
    -0.51
     model
    -0.49
    Filmografia
    -0.49
    !
    -0.49
    bred
    -0.49
    espé
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.80
    HomeAsUpEnabled
    0.76
     gynhyrchwyd
    0.74
    AnchorStyles
    0.71
    رشف
    0.69
     autorytatywna
    0.68
     يتيمه
    0.68
    хьтан
    0.67
     تانيه
    0.65
     kaynağından
    0.65
    Act Density 0.023%

    No Known Activations