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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spreading information or completing tasks

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     unexplained
    -0.69
    atan
    -0.66
     unknown
    -0.65
     incomp
    -0.63
    ilial
    -0.61
    zens
    -0.57
     unidentified
    -0.56
     burd
    -0.56
    gling
    -0.55
     inher
    -0.55
    POSITIVE LOGITS
     ASAP
    0.92
     sooner
    0.85
     quicker
    0.78
     cheaply
    0.77
     faster
    0.68
    istors
    0.68
    bin
    0.67
    vo
    0.63
     humming
    0.62
     easier
    0.62
    Act Density 0.207%

    No Known Activations