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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "do" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STANCE
    -0.14
    ocker
    -0.14
    igung
    -0.13
    insic
    -0.13
    nj
    -0.13
    OTA
    -0.13
    tering
    -0.13
    Äĥn
    -0.13
    _Syntax
    -0.13
     ëĦ¤ìĿ´íĬ¸
    -0.13
    POSITIVE LOGITS
     so
    0.97
    so
    0.56
     So
    0.46
    So
    0.44
     så
    0.42
    -so
    0.42
    _so
    0.40
    å¦ĤæѤ
    0.40
     ÑĤак
    0.40
    .so
    0.37
    Act Density 0.075%

    No Known Activations