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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Bunny
    -0.08
    sembly
    -0.06
    åĹ
    -0.06
     JADX
    -0.06
    amma
    -0.06
    iling
    -0.06
     vrát
    -0.06
     throw
    -0.06
    olumn
    -0.06
    ernel
    -0.06
    POSITIVE LOGITS
    룰
    0.07
    etheless
    0.06
    reno
    0.06
    .documentation
    0.06
    ¦y
    0.06
    opak
    0.06
    iendo
    0.06
    oten
    0.06
    rez
    0.06
    inel
    0.06
    Act Density 0.029%

    No Known Activations