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

    Neuronpedia

    INDEX
    Explanations

    expressions of praise and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clearance
    -0.32
    Cartesian
    -0.31
    XmlRootElement
    -0.30
    抽
    -0.30
     into
    -0.30
    color
    -0.29
     Pani
    -0.28
     colour
    -0.28
    let
    -0.28
     kleur
    -0.28
    POSITIVE LOGITS
     praise
    1.24
     admiration
    1.14
     praised
    1.13
    praise
    1.10
     Praise
    1.09
     praises
    1.09
     praising
    1.07
     applauded
    1.07
    Kudos
    1.06
     applaud
    1.03
    Act Density 0.255%

    No Known Activations