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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Instr
    -0.68
     earnest
    -0.64
     appe
    -0.63
     Barrett
    -0.61
     Buddy
    -0.60
     Pric
    -0.60
     substitute
    -0.59
     accountability
    -0.59
     Narr
    -0.58
     Amnesty
    -0.58
    POSITIVE LOGITS
    isoft
    1.12
    chwitz
    1.02
    ircraft
    0.98
    mble
    0.95
    ertain
    0.95
    redients
    0.95
    cean
    0.92
    mosp
    0.92
    duino
    0.91
    phal
    0.91
    Act Density 0.097%

    No Known Activations