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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or advancement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.69
    uded
    -0.68
    iciency
    -0.67
    ilies
    -0.65
    bryce
    -0.63
    iuses
    -0.61
    atur
    -0.60
    krit
    -0.59
    ateur
    -0.59
    unts
    -0.58
    POSITIVE LOGITS
     forward
    1.41
     forwards
    1.20
     toward
    1.16
     towards
    1.16
     onward
    1.11
    forward
    1.10
     ahead
    1.03
     Forward
    1.02
     onwards
    0.95
     backwards
    0.94
    Act Density 0.143%

    No Known Activations