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

    Neuronpedia

    INDEX
    Explanations

    financial terms related to fraud or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     feel
    -0.59
     feeling
    -0.55
     lenker
    -0.52
     feels
    -0.52
     FEEL
    -0.52
     really
    -0.50
     Feel
    -0.50
     mxArray
    -0.50
     your
    -0.49
     Page
    -0.49
    POSITIVE LOGITS
     auroit
    0.78
     preocupes
    0.76
     avoient
    0.73
     étoit
    0.71
     étoient
    0.71
     auffi
    0.70
     NDEBUG
    0.69
     ainfi
    0.68
    antaranya
    0.67
     feroit
    0.66
    Act Density 0.120%

    No Known Activations