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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is being kicked out of a group or place

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    interstitial
    -0.74
    OIL
    -0.69
    entle
    -0.68
    antry
    -0.64
    userc
    -0.64
    itational
    -0.62
    geries
    -0.62
    EY
    -0.62
    asus
    -0.62
    esa
    -0.61
    POSITIVE LOGITS
    ta
    0.76
    stretched
    0.74
    posts
    0.74
    lier
    0.73
    fitted
    0.67
    casts
    0.64
    heses
    0.63
     Surv
    0.63
    bur
    0.63
    matched
    0.62
    Act Density 7.538%

    No Known Activations