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

    Neuronpedia

    INDEX
    Explanations

    dynamic verbs that convey movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rips
    -0.15
    oh
    -0.15
    udd
    -0.14
    redi
    -0.14
    going
    -0.14
     Instructions
    -0.14
    reds
    -0.14
    pas
    -0.13
     Libert
    -0.13
     statistics
    -0.13
    POSITIVE LOGITS
     into
    0.26
     onto
    0.18
     away
    0.17
    into
    0.17
    oggle
    0.16
     Into
    0.16
    tle
    0.16
    .yy
    0.15
    akedown
    0.15
     Gon
    0.15
    Act Density 0.220%

    No Known Activations