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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptive phrases that convey positivity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disastrous
    -0.54
    ksis
    -0.52
    <bos>
    -0.52
     unsatisfactory
    -0.51
    Awful
    -0.47
     feeble
    -0.47
     perilous
    -0.45
    Unavailable
    -0.44
    ánica
    -0.43
     wretched
    -0.43
    POSITIVE LOGITS
    addGap
    0.72
     clean
    0.70
    êques
    0.69
    istoitu
    0.67
     AssemblyTitle
    0.65
    wapV
    0.64
    SharedDtor
    0.64
     Wikimedijinoj
    0.64
    ngdoc
    0.62
    oredCriteria
    0.62
    Act Density 0.115%

    No Known Activations