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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ftate
    -1.01
     myſelf
    -0.99
     itſelf
    -0.98
     ſtate
    -0.97
     purpoſe
    -0.96
     themſelves
    -0.95
     pleaſure
    -0.90
     whoſe
    -0.90
     raiſ
    -0.89
     himſelf
    -0.84
    POSITIVE LOGITS
    </i>
    0.67
    </b>
    0.60
     crossorigin
    0.58
     Del
    0.56
     समीक्षाएं
    0.55
     Mc
    0.55
     tanke
    0.54
     ‘
    0.54
     Ch
    0.53
    HasForeignKey
    0.53
    Act Density 0.173%

    No Known Activations