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

    Neuronpedia

    INDEX
    Explanations

    terms related to scrolling actions and navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekil
    -0.18
    ymbols
    -0.15
    ovice
    -0.15
    pire
    -0.15
    hoo
    -0.15
    elder
    -0.15
    assen
    -0.14
    cken
    -0.14
    ernals
    -0.14
    umo
    -0.14
    POSITIVE LOGITS
    Ļæ±Ł
    0.17
    able
    0.16
    ottom
    0.15
     naked
    0.15
     Ari
    0.14
    ghi
    0.14
    ing
    0.13
     Gil
    0.13
    abel
    0.13
    accion
    0.13
    Act Density 0.022%

    No Known Activations