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

    Neuronpedia

    INDEX
    Explanations

    technical terms and measures related to statistical analysis and modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     craindre
    -0.54
     irse
    -0.44
     adaptarse
    -0.42
     comunicarse
    -0.40
     Bergmann
    -0.39
     parvenir
    -0.39
     Brust
    -0.39
     Trock
    -0.39
     convaincre
    -0.38
    unschweig
    -0.37
    POSITIVE LOGITS
    aner
    0.91
    oler
    0.91
     Asher
    0.89
     Ader
    0.88
     Waller
    0.85
    anter
    0.85
     Niger
    0.85
     Beller
    0.85
     Azer
    0.84
    icer
    0.84
    Act Density 1.090%

    No Known Activations