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

    Neuronpedia

    INDEX
    Explanations

    concepts related to role models and examples of hope

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     prelimin
    -0.52
    Prelude
    -0.47
    ugier
    -0.43
     المعيارى
    -0.42
     PREL
    -0.42
     pamp
    -0.41
     come
    -0.41
    acyjna
    -0.40
    碰
    -0.39
    lander
    -0.39
    POSITIVE LOGITS
     Vorbild
    1.02
    IndentedString
    0.85
     imitated
    0.81
     imitate
    0.79
    estacks
    0.78
     copiar
    0.77
     exemplaires
    0.76
     imitating
    0.74
     emulate
    0.74
     péld
    0.73
    Act Density 0.107%

    No Known Activations