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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden movements or actions

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical movement or force

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.82
    sonian
    -0.58
    channelAvailability
    -0.57
    ãĤ·ãĥ£
    -0.57
     occurring
    -0.56
     longitudinal
    -0.55
     inhibition
    -0.55
    ministic
    -0.55
     deficiency
    -0.55
     plural
    -0.54
    POSITIVE LOGITS
    ushed
    1.03
    outed
    1.00
    armed
    0.95
    ammed
    0.91
    uked
    0.90
    ashed
    0.90
    rawled
    0.87
    elled
    0.85
    ounced
    0.85
    amped
    0.84
    Act Density 0.086%

    No Known Activations