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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.69
    principalColumn
    -0.58
    transQ
    -0.56
    あく
    -0.50
    あくまで
    -0.49
    日閲覧
    -0.48
    jmniej
    -0.47
    Šaltiniai
    -0.47
     вікі
    -0.47
     Sehr
    -0.45
    POSITIVE LOGITS
     better
    0.52
     anyone
    0.51
    PropertyChanging
    0.50
     imaginable
    0.48
    anyone
    0.48
     leps
    0.45
     sweeter
    0.44
     ANYONE
    0.44
    Anyone
    0.44
     anything
    0.43
    Act Density 0.291%

    No Known Activations