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

    Neuronpedia

    INDEX
    Explanations

    terms related to professional job positions

    oai_token-act-pair · gpt-3.5-turbo

    references to job or leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BUG
    -0.79
    LET
    -0.75
    reb
    -0.75
    shield
    -0.72
    LECT
    -0.69
    STON
    -0.67
    Revolution
    -0.66
    scape
    -0.65
    PDATE
    -0.65
    Shield
    -0.64
    POSITIVE LOGITS
     positions
    1.15
    hops
    1.09
    paces
    1.07
    hips
    1.04
     roles
    1.02
    etting
    0.99
    manship
    0.96
    hare
    0.95
    mith
    0.95
    cius
    0.90
    Act Density 0.042%

    No Known Activations