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

    Neuronpedia

    INDEX
    Explanations

    entities associated with named persons

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "Sal"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dominion
    -0.80
    lihood
    -0.74
    STEP
    -0.71
     depreciation
    -0.71
    ãģĨ
    -0.70
     halftime
    -0.64
     Breaker
    -0.63
     fixme
    -0.63
     Nationwide
    -0.62
     clipboard
    -0.61
    POSITIVE LOGITS
    omon
    1.42
    isbury
    1.33
    mone
    1.29
    azar
    1.28
    adin
    1.20
    utations
    1.14
    afi
    1.09
    gado
    1.07
    amon
    1.07
    erno
    1.05
    Act Density 0.020%

    No Known Activations