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

    Neuronpedia

    INDEX
    Explanations

    plural nouns and present tense verbs indicating action or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    panic
    -0.15
    _overflow
    -0.14
     Rencontre
    -0.14
    lops
    -0.14
     contacted
    -0.14
    ulares
    -0.13
    ãĥ¼ãĥł
    -0.13
    ponge
    -0.13
     microseconds
    -0.13
     dipping
    -0.13
    POSITIVE LOGITS
     walk
    0.60
     Walk
    0.57
     walking
    0.57
    walk
    0.56
     walks
    0.56
    Walk
    0.55
    walking
    0.53
     walked
    0.52
     Walking
    0.51
    .walk
    0.49
    Act Density 0.018%

    No Known Activations