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

    Neuronpedia

    INDEX
    Explanations

    references to self or individual identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endphp
    -0.78
    intios
    -0.68
     autorytatywna
    -0.67
    PreferredItem
    -0.61
     مشين
    -0.61
    Personensuche
    -0.60
    بوابة
    -0.59
    íncia
    -0.58
     Савезне
    -0.54
    StructEnd
    -0.54
    POSITIVE LOGITS
    izes
    0.67
     realizes
    0.65
     transmits
    0.65
     describes
    0.63
     represents
    0.62
     delivers
    0.61
     chooses
    0.60
    Represents
    0.60
    Specifies
    0.60
     prays
    0.59
    Act Density 0.503%

    No Known Activations