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

    Neuronpedia

    INDEX
    Explanations

    sentences with questions or invitations suggesting interest in food or offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.59
    Биография
    -0.52
    Overall
    -0.51
    IsMutable
    -0.50
     []).
    -0.49
     Overall
    -0.48
    InjectAttribute
    -0.48
    AlterField
    -0.48
    </caption>
    -0.48
     myself
    -0.47
    POSITIVE LOGITS
     uyar
    0.69
     مرئيه
    0.63
    НИМА
    0.61
     Tiberius
    0.61
     Cæsar
    0.59
     virgins
    0.59
     thrills
    0.58
     Waray
    0.58
     simulated
    0.58
     الدولى
    0.58
    Act Density 0.167%

    No Known Activations