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

    Neuronpedia

    INDEX
    Explanations

    negative descriptions or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagHelper
    -0.90
    aspectj
    -0.73
    :✨
    -0.71
     Signalez
    -0.71
    CloseOperation
    -0.61
     FINDINGS
    -0.60
     lenker
    -0.58
    Clik
    -0.58
    ंदीखरीदारी
    -0.57
     ExecuteAsync
    -0.56
    POSITIVE LOGITS
     stupid
    3.15
    stupid
    2.78
     Stupid
    2.70
     dumb
    2.58
    Stupid
    2.53
     silly
    2.52
     foolish
    2.49
     idiotic
    2.33
     stupidity
    2.32
     idiot
    2.22
    Act Density 0.123%

    No Known Activations