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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a contrast or exception in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nagar
    -0.15
    ancellable
    -0.14
    orry
    -0.14
    ston
    -0.14
     إذ
    -0.14
    ilinear
    -0.13
    anka
    -0.13
    ROL
    -0.13
    ume
    -0.13
    usto
    -0.13
    POSITIVE LOGITS
    ERO
    0.15
    andy
    0.14
     Jahres
    0.14
    ernals
    0.14
    itage
    0.14
    ãĤ±ãĥĥãĥĪ
    0.14
     Mare
    0.14
    /views
    0.14
    endo
    0.14
    sticky
    0.13
    Act Density 0.017%

    No Known Activations