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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating a connection to a particular topic or subject matter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptions
    -0.16
    rav
    -0.16
    rah
    -0.15
    iw
    -0.15
    yle
    -0.15
    rite
    -0.15
    elters
    -0.15
    EI
    -0.15
    ruz
    -0.14
     Warren
    -0.14
    POSITIVE LOGITS
    ness
    0.25
    èģĶ
    0.17
    anon
    0.16
    LY
    0.16
    ly
    0.16
    evice
    0.16
    iability
    0.15
    erdale
    0.14
    æĸ¼
    0.14
    issent
    0.14
    Act Density 0.022%

    No Known Activations