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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or references within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spawn
    -0.83
    ieri
    -0.80
    stall
    -0.75
    orbit
    -0.72
    illion
    -0.69
    ibaba
    -0.67
    urrection
    -0.66
    ivas
    -0.66
    strate
    -0.66
    Saharan
    -0.65
    POSITIVE LOGITS
     regards
    1.08
     regard
    1.08
    draw
    1.00
     impunity
    0.91
     ease
    0.82
     dignity
    0.81
     confidence
    0.81
    drawn
    0.77
     hashtag
    0.76
     respect
    0.75
    Act Density 0.082%

    No Known Activations