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

    Neuronpedia

    INDEX
    Explanations

    information related to political conflicts and physical actions or situations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     CTR
    -0.81
    amba
    -0.78
     averages
    -0.78
     lifetime
    -0.77
    lav
    -0.76
    umn
    -0.74
    ushi
    -0.69
     Mercury
    -0.69
     Plum
    -0.68
     Peach
    -0.68
    POSITIVE LOGITS
    isance
    1.02
    ":"","
    0.98
    Aid
    0.85
    elight
    0.85
     throats
    0.82
     hyster
    0.80
     bandwagon
    0.76
    FIELD
    0.76
    moil
    0.76
    waves
    0.76
    Act Density 16.790%

    No Known Activations