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

    Neuronpedia

    INDEX
    Explanations

    expressions of amazement or admiration

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ELDS
    -0.59
    ークル
    -0.57
     wenn
    -0.54
    unusual
    -0.54
     Humor
    -0.54
    ISTRO
    -0.54
    ContentAsync
    -0.53
    baidu
    -0.53
    skosten
    -0.53
    uyla
    -0.53
    POSITIVE LOGITS
     feats
    0.90
    amazing
    0.90
     Incredible
    0.90
     incroy
    0.86
    Amazing
    0.84
     Amazing
    0.83
     amazing
    0.82
     incredi
    0.82
    AMAZING
    0.82
     Lein
    0.81
    Act Density 0.024%

    No Known Activations