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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical and technical information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Factor
    -0.66
    DERR
    -0.64
    antha
    -0.62
     multiplication
    -0.59
    Numbers
    -0.59
     GPA
    -0.57
    ategory
    -0.57
    ultz
    -0.56
    assian
    -0.56
    artney
    -0.55
    POSITIVE LOGITS
    bold
    0.84
    ges
    0.83
     Machina
    0.74
    tel
    0.73
    zel
    0.73
    berman
    0.73
    e
    0.73
    llo
    0.72
    ÃŁ
    0.72
    egu
    0.71
    Act Density 0.341%

    No Known Activations