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

    Neuronpedia

    INDEX
    Explanations

    interactions involving requests and replies, particularly in a conversational context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Bran
    -0.53
     immédi
    -0.53
    RegistryLite
    -0.52
    umbang
    -0.52
    deauna
    -0.51
     lettre
    -0.50
     noDo
    -0.50
     Explora
    -0.49
     sää
    -0.48
    chau
    -0.48
    POSITIVE LOGITS
     continue
    0.59
     continued
    0.54
    --;
    0.54
     continues
    0.52
    DataAnnotations
    0.52
    RenderAtEndOf
    0.51
    continued
    0.50
    )];
    0.50
    oby
    0.49
    abestanden
    0.48
    Act Density 0.113%

    No Known Activations