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

    Neuronpedia

    INDEX
    Explanations

    product names or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to cancer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.77
    ibly
    -0.70
    dozen
    -0.66
    eways
    -0.64
    actively
    -0.63
    efully
    -0.61
    bern
    -0.61
    bably
    -0.59
    rather
    -0.59
    assed
    -0.58
    POSITIVE LOGITS
     performs
    0.85
     is
    0.80
     delivers
    0.78
     Profile
    0.78
     welcomes
    0.77
     Overview
    0.75
     enters
    0.74
     Discussion
    0.73
     Productions
    0.72
     Presents
    0.72
    Act Density 0.261%

    No Known Activations