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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical content and instructions

    oai_token-act-pair · gpt-3.5-turbo

    the prepositions "to" and "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mone
    -0.73
    peat
    -0.73
     reps
    -0.70
    ¯
    -0.66
    lease
    -0.65
    Ryan
    -0.64
     toget
    -0.63
    daq
    -0.63
    repre
    -0.63
    bet
    -0.62
    POSITIVE LOGITS
     Aging
    1.06
     Decay
    0.90
     Hits
    0.86
     Ends
    0.86
     Owners
    0.86
     Scale
    0.86
     Bullets
    0.86
     Coverage
    0.85
     Influence
    0.85
     Removal
    0.85
    Act Density 0.370%

    No Known Activations