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

    Neuronpedia

    INDEX
    Explanations

    names and titles of individuals and entities within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourg
    -0.17
    ÑĢÑĥд
    -0.17
    £
    -0.16
     ãĤŃãĥ£
    -0.16
    orsi
    -0.15
    ongoose
    -0.15
    ytt
    -0.15
    umber
    -0.15
    ruz
    -0.15
    onica
    -0.14
    POSITIVE LOGITS
     h
    0.15
     bent
    0.15
     analogue
    0.15
    atu
    0.14
     Lim
    0.14
     s
    0.14
     Cul
    0.14
     folded
    0.14
     pu
    0.13
     Alma
    0.13
    Act Density 0.448%

    No Known Activations