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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hearth
    -0.73
    $.
    -0.68
     attRot
    -0.68
     Sakura
    -0.65
     ___
    -0.60
     Females
    -0.60
    .''.
    -0.59
     Melody
    -0.57
    Area
    -0.57
     Pathfinder
    -0.57
    POSITIVE LOGITS
     oversaw
    1.14
     resigned
    1.08
     announced
    1.06
     testified
    1.06
     congratulated
    1.05
     reiterated
    1.04
     denounced
    1.04
     warned
    1.04
    enegger
    1.03
     argued
    1.02
    Act Density 0.285%

    No Known Activations