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

    Neuronpedia

    INDEX
    Explanations

    phrases that express skepticism or critique regarding claims and assertions of authority or credibility

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

    Statements or claims being made

    np_acts-logits-general · gemini-2.0-flash

    declarations and claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.76
    Disliked
    -0.61
     appreciation
    -0.60
     Appreciation
    -0.59
    Xna
    -0.57
    HostException
    -0.56
     JpaRepository
    -0.53
    ForRow
    -0.53
    astify
    -0.52
     JAXBElement
    -0.51
    POSITIVE LOGITS
     claim
    2.99
     claims
    2.92
     claimed
    2.86
     claiming
    2.75
     Claims
    2.58
     Claim
    2.57
    claim
    2.56
     CLAIM
    2.53
    claims
    2.46
    Claim
    2.43
    Act Density 0.502%

    No Known Activations