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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.61
     
    -0.60
     vol
    -0.59
     "
    -0.58
    vol
    -0.58
     The
    -0.56
    mid
    -0.56
     &
    -0.54
     '
    -0.54
    0
    -0.54
    POSITIVE LOGITS
     pleaſure
    1.17
     myſelf
    1.08
     preſent
    0.98
     ſtate
    0.97
     itſelf
    0.97
    ⓧ
    0.93
     ſhe
    0.92
     ſche
    0.92
    +#+
    0.91
     greateſt
    0.91
    Act Density 0.402%

    No Known Activations