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

    Neuronpedia

    INDEX
    Explanations

    references to different modes or types within a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dale
    -0.22
    anta
    -0.20
    mer
    -0.17
    ty
    -0.16
    aph
    -0.16
    ming
    -0.16
    nt
    -0.15
    awy
    -0.15
    min
    -0.15
    raph
    -0.15
    POSITIVE LOGITS
    hift
    0.21
    led
    0.17
    ities
    0.17
     operand
    0.17
    езд
    0.16
    ality
    0.16
    mium
    0.16
    lessly
    0.16
    ovan
    0.16
    ButtonItem
    0.16
    Act Density 0.018%

    No Known Activations