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

    Neuronpedia

    INDEX
    Explanations

    the presence of a specific negative feature or condition

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Utf
    -0.49
    DebuggerNonUser
    -0.46
     JAXB
    -0.45
    PrototypeOf
    -0.44
    wikkel
    -0.43
    IsContent
    -0.41
     Bioaccumulative
    -0.41
     toiminta
    -0.41
    q
    -0.41
     mutlu
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.81
    ⓧ
    0.77
     мәкал
    0.77
     חיצוניים
    0.76
    Autoritní
    0.73
     تانيه
    0.71
    SharedDtor
    0.66
    sizeCache
    0.66
    RTEX
    0.65
     ExecuteAsync
    0.63
    Act Density 0.000%

    No Known Activations