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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and their contextual usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iens
    -0.18
    tÃŃ
    -0.15
    middlewares
    -0.14
    tdown
    -0.13
    cid
    -0.13
    iy
    -0.13
    mak
    -0.13
    VK
    -0.13
     determination
    -0.13
    668
    -0.13
    POSITIVE LOGITS
     used
    0.34
    used
    0.30
     Used
    0.26
    çĶ¨äºİ
    0.26
    Used
    0.25
     USED
    0.25
     use
    0.24
    _used
    0.24
    -used
    0.24
     employed
    0.23
    Act Density 0.220%

    No Known Activations