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

    Neuronpedia

    INDEX
    Explanations

    contrasts and concessions in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zwar
    -0.16
    /generated
    -0.15
    instein
    -0.14
    ulong
    -0.14
    .simps
    -0.14
    gren
    -0.14
    ardy
    -0.14
    okt
    -0.14
    ạ
    -0.14
     sogar
    -0.14
    POSITIVE LOGITS
    inton
    0.18
    ASP
    0.15
    IPS
    0.14
     sheer
    0.14
    ch
    0.14
     pure
    0.14
     ensuring
    0.14
     handful
    0.14
    ãĥ©ãĤ¯
    0.13
    standing
    0.13
    Act Density 0.087%

    No Known Activations