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

    Neuronpedia

    INDEX
    Explanations

    terms related to minimum requirements or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     APT
    -0.71
     exceptionnelle
    -0.67
     DAI
    -0.65
    bB
    -0.63
    binant
    -0.63
     exceptionnel
    -0.62
     Christen
    -0.62
     sobra
    -0.61
    ########.
    -0.61
    actylus
    -0.61
    POSITIVE LOGITS
     elimination
    0.89
     eliminate
    0.87
    elimin
    0.86
     "../../../
    0.85
    ../../
    0.84
     Elimination
    0.83
    élimin
    0.83
     '../../../../
    0.79
    theless
    0.78
     pores
    0.77
    Act Density 0.133%

    No Known Activations