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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions, dependencies, or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fatal
    -0.15
    antan
    -0.15
    eters
    -0.15
    688
    -0.14
    ek
    -0.14
    ulin
    -0.13
     воÑĢ
    -0.13
    -eye
    -0.13
    achel
    -0.13
    udas
    -0.13
    POSITIVE LOGITS
    essim
    0.16
    -in
    0.14
    wind
    0.14
    éŃĤ
    0.14
    yll
    0.14
    öy
    0.14
    ymph
    0.14
    mir
    0.13
    otland
    0.13
    /as
    0.13
    Act Density 0.056%

    No Known Activations