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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words

    oai_token-act-pair · gpt-3.5-turbo

    references to red-top headlines or sensationalist media structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tiny
    -0.83
     Tall
    -0.80
     Bull
    -0.78
     Helic
    -0.77
     Mystic
    -0.75
     Dynam
    -0.74
     Carnegie
    -0.74
     Tab
    -0.73
     Syl
    -0.73
     Virtual
    -0.72
    POSITIVE LOGITS
    based
    1.41
    level
    1.34
    enough
    1.33
    bearing
    1.32
    bodied
    1.31
    direction
    1.29
    related
    1.29
    deal
    1.28
    only
    1.28
    group
    1.28
    Act Density 0.139%

    No Known Activations