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

    Neuronpedia

    INDEX
    Explanations

    references to foundational or introductory elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    831
    -0.15
     causal
    -0.13
    morgan
    -0.13
    .Dom
    -0.13
     hallmark
    -0.13
    ÃŃsto
    -0.13
    icol
    -0.13
    atio
    -0.13
    ighet
    -0.13
     Scoped
    -0.13
    POSITIVE LOGITS
     starting
    0.57
    starting
    0.50
     reference
    0.49
     Starting
    0.48
    Starting
    0.47
    reference
    0.45
    Reference
    0.42
    -reference
    0.40
     Reference
    0.39
     guide
    0.39
    Act Density 0.155%

    No Known Activations