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

    Neuronpedia

    INDEX
    Explanations

    references to literary concepts and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adows
    -0.18
    ors
    -0.17
    तर
    -0.17
    uck
    -0.16
    нÑĤ
    -0.16
    venge
    -0.16
    APA
    -0.16
    sg
    -0.15
    indrome
    -0.15
    steen
    -0.15
    POSITIVE LOGITS
    urgical
    0.21
    /language
    0.20
    atur
    0.18
    inded
    0.18
    lle
    0.17
    -minded
    0.17
    ature
    0.17
     critic
    0.17
    /art
    0.16
     minded
    0.16
    Act Density 0.021%

    No Known Activations