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

    Neuronpedia

    INDEX
    Explanations

    words related to violent actions or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uits
    -0.84
    ships
    -0.79
    hips
    -0.78
    ooks
    -0.77
    inders
    -0.73
    lems
    -0.72
    osponsors
    -0.71
    emies
    -0.68
    ographics
    -0.67
    zos
    -0.67
    POSITIVE LOGITS
     hundred
    1.01
     unnamed
    1.01
     person
    0.93
     woman
    0.90
     unidentified
    0.87
     thousand
    0.83
     guy
    0.82
     participant
    0.81
     elderly
    0.80
     protester
    0.79
    Act Density 0.097%

    No Known Activations