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

    Neuronpedia

    INDEX
    Explanations

    words related to quick movement or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "jump" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĨãĤ£
    -0.75
    venge
    -0.69
    代
    -0.68
     Smile
    -0.67
     è£ı
    -0.65
     Restore
    -0.65
    minus
    -0.64
     Mobility
    -0.63
    ors
    -0.62
    tm
    -0.62
    POSITIVE LOGITS
    frog
    0.96
    olicy
    0.89
    uit
    0.86
    uits
    0.85
    osate
    0.83
    oons
    0.81
    started
    0.80
     overboard
    0.78
    start
    0.78
    fleet
    0.75
    Act Density 0.034%

    No Known Activations