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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members

    oai_token-act-pair · gpt-3.5-turbo

    references to family members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.82
    BAT
    -0.70
    spect
    -0.66
    yss
    -0.64
    Scope
    -0.64
    icol
    -0.63
     bloom
    -0.62
     Moor
    -0.62
    irgin
    -0.62
    jab
    -0.61
    POSITIVE LOGITS
    hips
    1.07
    Eva
    0.80
    holders
    0.78
     stationed
    0.74
    iblings
    0.72
    abilia
    0.72
     who
    0.70
    bilt
    0.68
    bery
    0.68
    ials
    0.66
    Act Density 0.042%

    No Known Activations