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

    Neuronpedia

    INDEX
    Explanations

    phrases related to naming and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utm
    -0.15
     embr
    -0.15
    lore
    -0.14
     GG
    -0.14
     Rh
    -0.14
     shrink
    -0.14
     lekker
    -0.13
    ÏĦÏį
    -0.13
    tru
    -0.13
    HP
    -0.13
    POSITIVE LOGITS
     Flint
    0.20
     Tone
    0.19
    Bundle
    0.19
    Kin
    0.17
     Kin
    0.17
     glyph
    0.17
     Bundle
    0.17
    bundle
    0.16
    ehen
    0.16
    Ton
    0.16
    Act Density 0.000%

    No Known Activations