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

    Neuronpedia

    INDEX
    Explanations

    terms related to effective strategies, responsible behavior, and making informed choices in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fuhr
    -0.51
    EJB
    -0.51
    ❮
    -0.49
     suffered
    -0.48
     дека
    -0.48
    ppas
    -0.47
    predicates
    -0.46
    IInterface
    -0.45
     ficando
    -0.45
    VertexBuffer
    -0.44
    POSITIVE LOGITS
    enough
    0.88
     enough
    0.83
    ItemBackground
    0.81
     healthy
    0.78
     reliable
    0.77
     sane
    0.76
     balanced
    0.73
     safe
    0.72
    localctx
    0.71
     adequate
    0.71
    Act Density 0.446%

    No Known Activations