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

    Neuronpedia

    INDEX
    Explanations

    words that convey emotional quality or evaluative judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ა
    -0.52
    <eos>
    -0.48
    wer
    -0.45
     or
    -0.44
    lah
    -0.44
     generally
    -0.44
     
    -0.43
    inc
    -0.43
    ime
    -0.42
    ்க
    -0.42
    POSITIVE LOGITS
     pleaſure
    1.34
     purpoſe
    1.34
     myſelf
    1.34
     raiſ
    1.31
     themſelves
    1.29
     houſe
    1.28
     itſelf
    1.27
     Efq
    1.27
     Monfieur
    1.25
     ſeveral
    1.25
    Act Density 0.973%

    No Known Activations