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

    Neuronpedia

    INDEX
    Explanations

    numerical values or codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.70
    phabet
    -0.66
     volunt
    -0.66
     nomine
    -0.66
     Nass
    -0.63
     compan
    -0.61
     Daytona
    -0.61
     Tonight
    -0.61
     nailed
    -0.60
     Charity
    -0.59
    POSITIVE LOGITS
    248
    1.14
    377
    1.13
    368
    1.12
    429
    1.10
    019
    1.10
    018
    1.10
    998
    1.08
    378
    1.07
    758
    1.07
    225
    1.07
    Act Density 0.044%

    No Known Activations