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

    Neuronpedia

    INDEX
    Explanations

    references to technology and online activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.77
    ittal
    -0.77
    uliffe
    -0.76
    idates
    -0.75
    igious
    -0.74
    istical
    -0.72
    ackers
    -0.70
    essing
    -0.69
     somew
    -0.69
    lyak
    -0.68
    POSITIVE LOGITS
    lihood
    1.20
     ours
    1.16
     hers
    0.97
     yours
    0.90
    lier
    0.78
     theirs
    0.77
     Dom
    0.74
    liest
    0.74
     those
    0.72
    those
    0.68
    Act Density 0.072%

    No Known Activations