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

    Neuronpedia

    INDEX
    Explanations

    qualifiers and adjectives that indicate certainty or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ityEngine
    -0.18
    ücken
    -0.17
    ITT
    -0.15
    feld
    -0.14
    _HERSHEY
    -0.14
    £½
    -0.14
    dek
    -0.14
     Malk
    -0.14
    vecs
    -0.14
    æ±
    -0.14
    POSITIVE LOGITS
    kem
    0.16
    eb
    0.14
    /etc
    0.14
    k
    0.14
    oly
    0.14
     Garc
    0.13
     outweigh
    0.13
     etc
    0.13
    Alias
    0.13
     Expected
    0.13
    Act Density 0.066%

    No Known Activations