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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or limitations imposed on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Subject to" phrase

    np_acts-logits-general · gemini-2.0-flash

    subject to condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TargetException
    -0.62
    StreetMap
    -0.49
    ALLY
    -0.48
    ParallelGroup
    -0.48
     NgModule
    -0.47
     mihi
    -0.47
    Mein
    -0.46
     Гото
    -0.46
     linkovi
    -0.46
    __':
    -0.46
    POSITIVE LOGITS
    addCriterion
    0.78
     Chwiliwch
    0.69
    InSection
    0.63
    EventLoop
    0.63
    AndEndTag
    0.62
     تضيفلها
    0.61
     rigue
    0.61
    twimg
    0.60
     scrutiny
    0.60
     considerable
    0.59
    Act Density 0.251%

    No Known Activations