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

    Neuronpedia

    INDEX
    Explanations

    instances of someone being hired or invited

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hired" and related employment terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggles
    -0.60
    herence
    -0.58
     correlations
    -0.57
    auer
    -0.56
    ipes
    -0.56
    nce
    -0.55
    fal
    -0.55
    loss
    -0.54
    zers
    -0.54
    dos
    -0.53
    POSITIVE LOGITS
     by
    1.23
     aback
    0.91
     to
    0.86
     BY
    0.85
     aboard
    0.79
    by
    0.76
    uled
    0.75
     into
    0.70
    enced
    0.68
     By
    0.68
    Act Density 0.150%

    No Known Activations