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

    Neuronpedia

    INDEX
    Explanations

    references to logical reasoning and justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.81
    contentLoaded
    -0.76
    Personensuche
    -0.71
    HasAnnotation
    -0.68
    aronder
    -0.66
    Parcelize
    -0.63
     polymorphism
    -0.63
     obstante
    -0.61
    ··
    -0.61
    #+#
    -0.61
    POSITIVE LOGITS
     logical
    2.16
     logic
    2.16
     Logic
    1.97
     Logical
    1.90
    Logical
    1.83
    logical
    1.78
    Logic
    1.76
     lógica
    1.73
     LOGIC
    1.67
    logic
    1.62
    Act Density 0.087%

    No Known Activations