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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating connection or sharing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Calibri
    -0.19
    ãĥŃãĥ¼
    -0.17
    ад
    -0.16
    aggable
    -0.16
    ainen
    -0.15
    ilde
    -0.15
    abee
    -0.15
    adt
    -0.15
    osti
    -0.15
    adb
    -0.15
    POSITIVE LOGITS
    ÌĤ
    0.17
    ari
    0.16
    μη
    0.14
    _ALLOW
    0.14
     Dist
    0.14
     ub
    0.14
    UB
    0.14
    cale
    0.14
    udi
    0.14
    ennon
    0.14
    Act Density 0.023%

    No Known Activations