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

    Neuronpedia

    INDEX
    Explanations

    words related to proper nouns or acronyms, specifically related to organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific labels or designations related to entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icum
    -0.77
    ply
    -0.76
    aqu
    -0.76
    peer
    -0.75
    ported
    -0.72
     scrut
    -0.71
    andre
    -0.70
    pron
    -0.70
    pill
    -0.70
     Debor
    -0.69
    POSITIVE LOGITS
    vernment
    0.95
    ORGE
    0.88
    roups
    0.86
    raphic
    0.86
    allery
    0.78
    rowth
    0.77
    irlfriend
    0.76
    ZA
    0.74
    glers
    0.73
    omez
    0.73
    Act Density 0.058%

    No Known Activations