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

    Neuronpedia

    INDEX
    Explanations

    references to "X" and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.40
    ագրություններ
    -0.39
    ValueGenerated
    -0.38
     primario
    -0.37
    المناصب
    -0.36
     Autorizaciones
    -0.36
     sizi
    -0.35
    mnar
    -0.35
     manuales
    -0.35
     vuelta
    -0.35
    POSITIVE LOGITS
     X
    0.60
    tend
    0.55
    ValueStyle
    0.52
    Tend
    0.50
    DIPSETTING
    0.49
    ray
    0.48
     autorytatywna
    0.47
    ayah
    0.46
     Tend
    0.46
    eno
    0.46
    Act Density 0.284%

    No Known Activations