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

    Neuronpedia

    INDEX
    Explanations

    claims or statements of ownership

    oai_token-act-pair · gpt-3.5-turbo

    claims made by individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.68
    hens
    -0.66
    YC
    -0.65
    oyer
    -0.64
    gam
    -0.64
    ioch
    -0.63
    mitt
    -0.63
    aldi
    -0.62
    storms
    -0.62
    FG
    -0.62
    POSITIVE LOGITS
    Downloadha
    0.93
     innocence
    0.82
     authenticity
    0.79
     sqor
    0.75
     paranormal
    0.70
     fabricated
    0.70
     supernatural
    0.70
     specificity
    0.69
    ĪĴ
    0.69
     deduction
    0.68
    Act Density 0.200%

    No Known Activations