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

    Neuronpedia

    INDEX
    Explanations

    assertive phrases that convey personal opinions or statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.88
    enderror
    -0.82
    èdia
    -0.78
    Geplaatst
    -0.77
     beginnetje
    -0.74
    :✨
    -0.71
    @[+][
    -0.69
    WebControls
    -0.65
    NameInMap
    -0.64
    addCriterion
    -0.64
    POSITIVE LOGITS
    TProtocol
    0.48
     ['./
    0.42
    </thead>
    0.42
    pattern
    0.41
    šča
    0.40
    ore
    0.39
    躇
    0.39
    celana
    0.39
     [{
    0.38
     CLIP
    0.38
    Act Density 0.034%

    No Known Activations