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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to writing and text creation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words related to types of intelligence or cognitive ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parenthood
    -0.74
    volent
    -0.73
    fml
    -0.71
    slaught
    -0.71
    fen
    -0.70
    pring
    -0.68
     Reserve
    -0.68
     Salvation
    -0.66
    isite
    -0.66
     reven
    -0.66
    POSITIVE LOGITS
    pict
    0.97
     arithmetic
    0.95
     PowerPoint
    0.93
     photographs
    0.92
     verse
    0.90
     deeds
    0.90
     deed
    0.89
     pictures
    0.88
     images
    0.87
     videot
    0.87
    Act Density 0.195%

    No Known Activations