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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss the meaning or interpretation of terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essian
    -0.19
    ickey
    -0.15
    uno
    -0.15
    iggs
    -0.14
    occo
    -0.14
    erview
    -0.14
    pcs
    -0.14
    ACS
    -0.14
    éĢŁåº¦
    -0.14
    aginator
    -0.13
    POSITIVE LOGITS
     Incontri
    0.14
     Guild
    0.14
    ÃĹ↵↵
    0.13
     ÐĿÑĸ
    0.13
    yb
    0.13
    verb
    0.13
    meld
    0.13
     Claude
    0.13
    ABLE
    0.13
    YO
    0.13
    Act Density 0.059%

    No Known Activations