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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong affirmations or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amment
    -0.16
    inaire
    -0.15
     PaÅŁa
    -0.14
    å¨
    -0.14
     Forbes
    -0.14
    inel
    -0.14
    ainless
    -0.14
    aec
    -0.14
    upa
    -0.14
    .Override
    -0.14
    POSITIVE LOGITS
     ‘
    0.16
    ijn
    0.15
     Bij
    0.15
    emean
    0.15
     -,
    0.15
     affair
    0.14
     /
    0.14
    uls
    0.14
    _kw
    0.14
    âr
    0.14
    Act Density 0.000%

    No Known Activations