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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that express uncertainty or highlight the act of doing in various contexts

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

    whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.71
    ScopeManager
    -0.60
    rungsseite
    -0.54
     disponibilités
    -0.54
    médiaire
    -0.53
    httphttps
    -0.53
    assas
    -0.51
    fael
    -0.50
     certes
    -0.49
     ujednoznacz
    -0.49
    POSITIVE LOGITS
    Whatever
    0.49
    whatever
    0.47
     whatever
    0.47
     Whatever
    0.44
    tvguidetime
    0.42
     Qualquer
    0.42
     Cualquier
    0.41
     qualquer
    0.41
     wherever
    0.40
    anything
    0.40
    Act Density 0.018%

    No Known Activations