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

    Neuronpedia

    INDEX
    Explanations

    actions related to adding or incorporating features or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.16
    cies
    -0.15
    ogl
    -0.15
    ulfilled
    -0.15
    «a
    -0.15
    coni
    -0.15
    /Area
    -0.14
    acho
    -0.14
     Biggest
    -0.14
    efeller
    -0.13
    POSITIVE LOGITS
    endum
    0.41
    ition
    0.36
    uce
    0.34
    -ons
    0.34
    resse
    0.33
    itive
    0.31
    itions
    0.30
    /sub
    0.29
    icted
    0.29
    itionally
    0.28
    Act Density 0.079%

    No Known Activations