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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and production processes

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to creation and structure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.71
    ©¶æ
    -0.63
    addons
    -0.63
     Volunte
    -0.62
     Grounds
    -0.61
     Paran
    -0.61
     Discord
    -0.60
     Bans
    -0.60
     precaution
    -0.58
    Gaming
    -0.57
    POSITIVE LOGITS
     indistinguishable
    0.86
     usable
    0.81
     lasting
    0.79
    uable
    0.79
    irable
    0.79
     instantly
    0.78
     equivalent
    0.75
     unlike
    0.74
     unparalleled
    0.74
     richer
    0.74
    Act Density 0.649%

    No Known Activations