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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and mathematical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Freed
    -0.66
    lish
    -0.66
    auga
    -0.65
    abre
    -0.65
    SPONSORED
    -0.65
    orian
    -0.64
    atl
    -0.63
    _-_
    -0.62
     Pillar
    -0.61
     braces
    -0.61
    POSITIVE LOGITS
    heter
    0.77
    REDACTED
    0.75
    âĪĴ
    0.73
     Nato
    0.71
     Crim
    0.70
    Discussion
    0.66
     antagonists
    0.64
     0
    0.63
     FDR
    0.62
     920
    0.61
    Act Density 0.030%

    No Known Activations