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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ageing
    -0.66
    quartered
    -0.65
     substitutes
    -0.63
     defense
    -0.63
     cooperative
    -0.62
     aging
    -0.61
     represented
    -0.60
    erella
    -0.60
     fertility
    -0.60
     retiring
    -0.59
    POSITIVE LOGITS
    twitter
    1.10
    cdn
    0.86
    #$
    0.83
    youtu
    0.79
    ðŁ
    0.79
    ://
    0.76
     Appears
    0.74
    âĢİ
    0.73
    à
    0.72
    usercontent
    0.71
    Act Density 0.012%

    No Known Activations