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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs indicating potential or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azor
    -0.16
    Breadcrumb
    -0.16
    itta
    -0.16
    _allow
    -0.16
    vik
    -0.15
    hq
    -0.15
     Allow
    -0.14
    iji
    -0.14
    é¡
    -0.14
     ----------------------------------------------------------------------------↵
    -0.13
    POSITIVE LOGITS
     worry
    0.18
     Crow
    0.18
     æ½
    0.16
     offer
    0.15
     crow
    0.15
    uste
    0.15
    sem
    0.15
     sem
    0.14
    cla
    0.14
    ugen
    0.14
    Act Density 0.045%

    No Known Activations