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

    Neuronpedia

    INDEX
    Explanations

    names of places and people

    oai_token-act-pair · gpt-3.5-turbo

    names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rhod
    -0.86
     Buffalo
    -0.85
     Reloaded
    -0.82
     Squirrel
    -0.76
     Reno
    -0.73
     Villa
    -0.72
     Butler
    -0.71
     Mud
    -0.71
     funnel
    -0.70
     420
    -0.69
    POSITIVE LOGITS
    IS
    1.84
    is
    1.73
    ises
    1.52
    isin
    1.39
    ise
    1.33
    isers
    1.32
     Kis
    1.27
    iss
    1.25
    isl
    1.24
    isse
    1.23
    Act Density 0.185%

    No Known Activations