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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITHUB
    -0.70
     kwiat
    -0.65
     Gerr
    -0.61
     breech
    -0.57
     Rani
    -0.57
     Marten
    -0.57
     Mejía
    -0.56
     Hoo
    -0.55
    Meno
    -0.55
    hpp
    -0.55
    POSITIVE LOGITS
    Personensuche
    0.76
    APORE
    0.66
    mybatisplus
    0.64
    UpDown
    0.64
    二十四
    0.60
    Suara
    0.58
    casio
    0.57
    LAR
    0.57
     الحره
    0.57
    >>()
    0.53
    Act Density 0.299%

    No Known Activations