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

    Neuronpedia

    INDEX
    Explanations

    references to third-party entities and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.76
    tagext
    -0.71
    IsContent
    -0.65
    +#+#
    -0.64
    RetentionPolicy
    -0.63
    usermodel
    -0.63
     estekak
    -0.62
    Попис
    -0.62
    ьаж
    -0.61
    usercontent
    -0.60
    POSITIVE LOGITS
     outside
    0.85
    outside
    0.75
     external
    0.71
     guest
    0.69
     Guest
    0.68
     Outside
    0.67
     terceros
    0.67
     خارجی
    0.64
     terceiros
    0.64
     externes
    0.64
    Act Density 0.470%

    No Known Activations