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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities or events in motion

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs related to movement or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.65
     coron
    -0.62
    ongyang
    -0.61
    ruary
    -0.58
    boa
    -0.58
     ratified
    -0.57
     plum
    -0.56
    ufact
    -0.55
    inctions
    -0.55
    avorite
    -0.54
    POSITIVE LOGITS
    liest
    0.77
    waters
    0.76
     leash
    0.69
     confines
    0.66
    waves
    0.65
    pter
    0.63
    forts
    0.61
    aders
    0.61
    elight
    0.61
    âĶĢâĶĢ
    0.60
    Act Density 0.165%

    No Known Activations