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

    Neuronpedia

    INDEX
    Explanations

    phrases and references to self-awareness and personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HostException
    -0.63
    !*\
    -0.63
    PreExecute
    -0.60
    aspectj
    -0.60
    __':
    -0.59
    NOPQRST
    -0.59
    verifyException
    -0.59
    enumi
    -0.58
    IVEREF
    -0.57
    RuleContext
    -0.56
    POSITIVE LOGITS
    ChrTalk
    0.58
    发表于
    0.58
     Cosplay
    0.56
    cosplay
    0.52
     cosplay
    0.49
    moe
    0.49
     AspNetCore
    0.48
     otaku
    0.48
    saraba
    0.47
     Böl
    0.46
    Act Density 0.316%

    No Known Activations