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

    Neuronpedia

    INDEX
    Explanations

    terms related to preventing or blocking actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĢин
    -0.15
    arity
    -0.15
    eron
    -0.15
    GI
    -0.14
    cean
    -0.14
    æ£ļ
    -0.14
    bug
    -0.14
    erge
    -0.14
    eres
    -0.14
    alah
    -0.13
    POSITIVE LOGITS
    ormal
    0.16
    /mit
    0.16
    AGED
    0.15
    reno
    0.14
    odiac
    0.14
    orthy
    0.14
    787
    0.13
    -motion
    0.13
    emble
    0.13
    exe
    0.13
    Act Density 0.032%

    No Known Activations