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

    Neuronpedia

    INDEX
    Explanations

    negative or contrasting sentiments expressed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usch
    -0.16
    âb
    -0.15
    nett
    -0.15
    anik
    -0.15
    /from
    -0.15
     Bri
    -0.14
    iad
    -0.14
    amble
    -0.14
    uso
    -0.14
    /of
    -0.14
    POSITIVE LOGITS
    LOUR
    0.14
    AREST
    0.13
    ä¹İ
    0.13
     wr
    0.13
    erville
    0.13
    æľĭ
    0.13
     viewer
    0.13
    à¥įद
    0.12
     Flores
    0.12
     verst
    0.12
    Act Density 0.009%

    No Known Activations