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

    Neuronpedia

    INDEX
    Explanations

    concepts related to minimalism and minimal solutions in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    y
    -0.67
     larga
    -0.67
    tagext
    -0.64
    h
    -0.63
    ul
    -0.59
     mouth
    -0.59
    ing
    -0.58
     ๆ
    -0.57
     htons
    -0.57
     atof
    -0.57
    POSITIVE LOGITS
    évaluateur
    0.95
    脚注の使い方
    0.91
    )++;
    0.89
    ^(@)
    0.88
    تفصیلات
    0.87
    Identyfik
    0.86
    theless
    0.81
    Cyfeiriadau
    0.81
    expandindo
    0.81
    ]),
    0.80
    Act Density 0.010%

    No Known Activations