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

    Neuronpedia

    INDEX
    Explanations

    phrases related to choices and decisions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ::$_
    -0.73
     didReceive
    -0.66
    gale
    -0.66
    XmlType
    -0.59
     Thoma
    -0.57
    ourable
    -0.56
    خخ
    -0.56
    plant
    -0.55
    มาะ
    -0.55
    Tung
    -0.54
    POSITIVE LOGITS
     Bhatt
    0.83
    SequentialGroup
    0.78
     Comprometido
    0.76
     oop
    0.75
    fjspx
    0.70
     PAZ
    0.68
    MemoryWarning
    0.67
    yszer
    0.64
    ANDUM
    0.64
    enegro
    0.63
    Act Density 0.029%

    No Known Activations