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

    Neuronpedia

    INDEX
    Explanations

    words related to specific professions or activities, like "gamblers" or "explorers"

    oai_token-act-pair · gpt-3.5-turbo

    plurals and descriptors related to various groups of people or professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angan
    -0.72
    Aw
    -0.67
    ASED
    -0.65
     revocation
    -0.63
     Matters
    -0.62
    AAAAAAAA
    -0.62
     Amendments
    -0.61
    ANA
    -0.61
     Integrity
    -0.60
     executions
    -0.60
    POSITIVE LOGITS
    hip
    1.40
    paces
    1.25
     beware
    1.13
    hips
    1.13
    pace
    1.09
    ervatives
    1.06
    mith
    1.05
     who
    0.99
     rejoice
    0.95
     extraord
    0.90
    Act Density 0.194%

    No Known Activations