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

    Neuronpedia

    INDEX
    Explanations

    action verbs and phrases related to movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     же
    -0.19
    onec
    -0.18
    hurst
    -0.16
    REAM
    -0.15
    fts
    -0.14
    ANS
    -0.14
    rafted
    -0.14
    rets
    -0.14
    gnore
    -0.14
    auen
    -0.14
    POSITIVE LOGITS
    out
    0.31
    ings
    0.30
    down
    0.28
    able
    0.28
    away
    0.28
    over
    0.27
    -up
    0.27
    -down
    0.27
    -through
    0.26
    aroo
    0.26
    Act Density 0.164%

    No Known Activations