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

    Neuronpedia

    INDEX
    Explanations

    references to long-term outcomes or durations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     lenght
    -0.98
    تقاوى
    -0.93
     duration
    -0.92
     length
    -0.91
     SHORT
    -0.89
    GetLength
    -0.83
    Short
    -0.81
     short
    -0.81
    SHORT
    -0.80
     LENGTH
    -0.80
    POSITIVE LOGITS
    UVWXYZ
    0.65
    anceled
    0.60
     Tyl
    0.60
    Slf
    0.60
     Sok
    0.60
     Laz
    0.59
     Ziegler
    0.59
    idyl
    0.57
     Z
    0.57
    SIG
    0.57
    Act Density 0.024%

    No Known Activations