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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical action or movement

    oai_token-act-pair · gpt-3.5-turbo

    the word "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CLSID
    -0.75
    gee
    -0.66
     Abyss
    -0.65
    >"
    -0.65
    =]
    -0.63
     Fidel
    -0.62
    Maker
    -0.60
    ]"
    -0.60
     Sorceress
    -0.60
    jah
    -0.59
    POSITIVE LOGITS
    stairs
    0.95
    dates
    0.90
    grades
    0.83
    river
    0.83
    rights
    0.82
    olicy
    0.79
    votes
    0.76
    dating
    0.75
    skirts
    0.75
    adesh
    0.75
    Act Density 0.110%

    No Known Activations