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

    Neuronpedia

    INDEX
    Explanations

    drug-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of uppercase letters or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.75
    wcsstore
    -0.69
    oufl
    -0.66
    ×ij
    -0.64
     DEFENSE
    -0.63
    WOR
    -0.63
     ACTIONS
    -0.62
     OPER
    -0.61
     FIN
    -0.61
     substitutes
    -0.61
    POSITIVE LOGITS
    etch
    0.74
    tarian
    0.73
    tarians
    0.71
    cks
    0.71
    td
    0.70
    vable
    0.68
     Citiz
    0.66
    mx
    0.65
    ifter
    0.65
    tn
    0.65
    Act Density 0.137%

    No Known Activations