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

    Neuronpedia

    INDEX
    Explanations

    words related to political accountability and denials involving accusations

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

    denial or refutation

    np_acts-logits-general · gemini-2.0-flash

    denial and refutation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.47
     gogh
    -0.47
    mapStateToProps
    -0.46
     Nark
    -0.46
    dür
    -0.45
    FormTagHelper
    -0.45
     Höhe
    -0.43
     Grav
    -0.42
     segn
    -0.42
    Fol
    -0.41
    POSITIVE LOGITS
     refute
    1.48
     refuted
    1.42
     deny
    1.40
     denies
    1.35
     denial
    1.35
     denying
    1.32
     denied
    1.30
     rebuttal
    1.28
     disprove
    1.25
     deb
    1.25
    Act Density 0.432%

    No Known Activations