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

    Neuronpedia

    INDEX
    Explanations

    instances of various nouns related to discussion, analysis, and choice-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izio
    -0.20
    oids
    -0.16
    æŁ³
    -0.15
    AGER
    -0.15
    opis
    -0.14
    urance
    -0.14
    iglia
    -0.14
    stants
    -0.14
    agna
    -0.14
    .AF
    -0.13
    POSITIVE LOGITS
    ÑĢид
    0.18
     apl
    0.16
     such
    0.15
     like
    0.15
     GAL
    0.15
    umi
    0.14
    veral
    0.14
    inned
    0.14
    0.14
    azz
    0.14
    Act Density 0.280%

    No Known Activations