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

    Neuronpedia

    INDEX
    Explanations

    multiple occurrences of the word "In" used to indicate introductory statements or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    activ
    -0.15
    òa
    -0.15
    gado
    -0.15
    sky
    -0.14
    wind
    -0.14
    pts
    -0.14
    verts
    -0.14
    елен
    -0.13
    alse
    -0.13
    olumn
    -0.13
    POSITIVE LOGITS
    AREST
    0.15
    iaux
    0.15
    à¹Īà¸Ńย
    0.14
    IDD
    0.13
    adam
    0.13
    istro
    0.13
    ´Ī
    0.13
    ÑĤаж
    0.13
    -bootstrap
    0.13
    oyer
    0.13
    Act Density 0.146%

    No Known Activations