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

    Neuronpedia

    INDEX
    Explanations

    terms related to avoidance and evasion strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endwhile
    -0.69
     ragione
    -0.64
    savevideo
    -0.61
     caufe
    -0.59
    endwhile
    -0.56
     aufgehoben
    -0.56
     flexível
    -0.56
    QFont
    -0.54
     endometri
    -0.54
    BufferException
    -0.54
    POSITIVE LOGITS
     Avoid
    0.75
    Avoid
    0.71
     avoid
    0.65
     AVOID
    0.65
     avoided
    0.65
    avoid
    0.62
    ArrowToggle
    0.62
     avoids
    0.62
    enumi
    0.58
     оригіналу
    0.57
    Act Density 0.367%

    No Known Activations