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

    Neuronpedia

    INDEX
    Explanations

    technical or specialized terms in various fields such as medicine, science, architecture, and activism

    oai_token-act-pair · gpt-3.5-turbo

    topics related to various forms of media, achievements, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steps
    -0.91
    Ĥİ
    -0.87
    fixes
    -0.83
    changes
    -0.81
     ACTIONS
    -0.81
    icides
    -0.79
    tics
    -0.78
    rams
    -0.78
    azes
    -0.78
    amples
    -0.77
    POSITIVE LOGITS
     resemblance
    1.13
     pedigree
    1.11
     knack
    1.09
     tendency
    1.04
     reputation
    1.02
     rating
    1.01
     mentality
    1.01
     penchant
    0.99
     fetish
    0.95
     nickname
    0.95
    Act Density 0.347%

    No Known Activations