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

    Neuronpedia

    INDEX
    Explanations

    verbs related to 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
     Smile
    -0.69
    minus
    -0.69
    venge
    -0.64
    ors
    -0.60
    been
    -0.60
     Mobility
    -0.60
    代
    -0.60
    tm
    -0.59
    è¯
    -0.59
    ãĥĨãĤ£
    -0.59
    POSITIVE LOGITS
    started
    0.88
    start
    0.87
    frog
    0.86
    lights
    0.85
     overboard
    0.84
    starter
    0.83
    starting
    0.82
    fleet
    0.77
     rope
    0.76
    oons
    0.76
    Act Density 0.029%

    No Known Activations