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

    Neuronpedia

    INDEX
    Explanations

    statements that express uncertainty or skepticism

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to skepticism and doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heights
    -0.60
    akedown
    -0.60
     tre
    -0.57
     suicidal
    -0.57
     hallucinations
    -0.57
     ancestor
    -0.55
     wired
    -0.55
     rall
    -0.54
     tresp
    -0.54
     enthus
    -0.53
    POSITIVE LOGITS
     sidx
    0.81
    actionDate
    0.80
    ãĤ«
    0.76
    ãĤº
    0.73
    oway
    0.72
    PsyNetMessage
    0.72
     thereto
    0.72
    EGA
    0.71
    ãĤ¿
    0.71
    ãĤ§
    0.70
    Act Density 0.218%

    No Known Activations