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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phous
    -0.77
    hibian
    -0.76
     كومونز
    -0.68
    subpackage
    -0.66
    ]='\
    -0.66
    entle
    -0.64
    jarat
    -0.64
    uldade
    -0.63
     rhestr
    -0.63
    fromnode
    -0.62
    POSITIVE LOGITS
    发表于
    0.74
     nulle
    0.73
     يتيمه
    0.70
    zeros
    0.66
     nothingness
    0.65
    NullException
    0.63
    0
    0.62
     '\\;'
    0.60
     cero
    0.57
     Coward
    0.57
    Act Density 0.456%

    No Known Activations