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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opinions or beliefs about situations or actions

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

    I don't think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.82
    SequentialGroup
    -0.63
     firebaseConfig
    -0.58
    expandindo
    -0.57
     мәкал
    -0.57
    Jîn
    -0.57
    encodeWith
    -0.56
     Wikimedijinoj
    -0.56
    TestingModule
    -0.54
    ſelf
    -0.53
    POSITIVE LOGITS
     évent
    0.41
     hipó
    0.40
     possibly
    0.36
     quaisquer
    0.36
     possible
    0.36
     가능
    0.36
     quelconque
    0.35
    rungsseite
    0.35
     kerugian
    0.35
     Perlu
    0.35
    Act Density 0.043%

    No Known Activations