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

    Neuronpedia

    INDEX
    Explanations

    discussions around morality and societal values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.66
     دیکھیے
    -0.47
     JADX
    -0.47
    mesine
    -0.47
     αυτή
    -0.46
    OrCreate
    -0.45
    AndEndTag
    -0.44
     jadx
    -0.44
     Orrell
    -0.44
    mog
    -0.43
    POSITIVE LOGITS
     unknown
    0.85
     unexpected
    0.79
     sublime
    0.76
     known
    0.73
     unthinkable
    0.69
    VIOUS
    0.68
     Unknown
    0.68
     obvious
    0.67
     Known
    0.66
     متعلقه
    0.66
    Act Density 0.090%

    No Known Activations