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

    Neuronpedia

    INDEX
    Explanations

    references to panels in discussions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emark
    -0.19
    afone
    -0.17
    es
    -0.16
    emp
    -0.15
    ening
    -0.15
    ess
    -0.15
    esin
    -0.15
     filmer
    -0.15
    ema
    -0.15
    onent
    -0.15
    POSITIVE LOGITS
    led
    0.32
    ists
    0.27
    ize
    0.24
    ing
    0.22
    ized
    0.21
    ayout
    0.21
    icious
    0.20
    lic
    0.20
    lica
    0.19
     discussion
    0.19
    Act Density 0.016%

    No Known Activations