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

    Neuronpedia

    INDEX
    Explanations

    references to components or elements within a larger context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hots
    -0.19
    ette
    -0.17
    hammer
    -0.17
    yat
    -0.17
    hair
    -0.17
    erin
    -0.16
    rb
    -0.16
    erator
    -0.16
    lah
    -0.16
    s
    -0.16
    POSITIVE LOGITS
    isans
    0.32
    aking
    0.32
    icular
    0.30
    ake
    0.25
    icipant
    0.24
    isan
    0.24
    icipation
    0.23
    icip
    0.23
    ook
    0.22
    ners
    0.22
    Act Density 0.079%

    No Known Activations