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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Good" and related positive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.17
    tant
    -0.16
    ulty
    -0.15
    _DEFINE
    -0.15
    ickey
    -0.15
    lobal
    -0.15
    eger
    -0.14
    á»ijng
    -0.14
    arily
    -0.14
    iggers
    -0.14
    POSITIVE LOGITS
    win
    0.27
    bye
    0.26
    rich
    0.23
     Samar
    0.23
     morning
    0.22
     Morning
    0.22
    wins
    0.22
    ison
    0.21
    ness
    0.21
    WIN
    0.21
    Act Density 0.020%

    No Known Activations