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

    Neuronpedia

    INDEX
    Explanations

    references to winning or losing streaks in sports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTED
    -0.74
    acus
    -0.72
    abad
    -0.67
     GOODMAN
    -0.67
    gency
    -0.66
    ocate
    -0.66
     Lod
    -0.65
    affer
    -0.64
    Sov
    -0.64
    onomic
    -0.64
    POSITIVE LOGITS
     streak
    1.13
    uous
    0.86
    iness
    0.84
     spanning
    0.80
    icity
    0.80
     streaks
    0.80
     lasting
    0.77
    isSpecialOrderable
    0.73
    lasting
    0.73
     dating
    0.72
    Act Density 0.038%

    No Known Activations