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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job recruitment or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    words and suffixes related to occupations, roles, and social identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GoldMagikarp
    -0.61
    Font
    -0.61
    ãĤ¯
    -0.61
    ilogy
    -0.61
    aceous
    -0.58
    izoph
    -0.57
    Aw
    -0.57
     Reaper
    -0.57
     srfAttach
    -0.57
    ipes
    -0.57
    POSITIVE LOGITS
     alike
    1.21
     who
    1.17
    hip
    1.09
    hips
    1.05
    '
    1.03
     whom
    0.97
    '/
    0.96
    ktop
    0.86
     stationed
    0.86
    who
    0.85
    Act Density 0.247%

    No Known Activations