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

    Neuronpedia

    INDEX
    Explanations

    the word "prior" and variations of it, indicating a focus on establishing temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.17
    elia
    -0.17
    vin
    -0.17
    all
    -0.16
    down
    -0.16
    edly
    -0.15
    ogg
    -0.15
    گرÛĮ
    -0.15
    onto
    -0.15
    chin
    -0.15
    POSITIVE LOGITS
    itized
    0.25
    itize
    0.22
    ities
    0.21
    itaire
    0.19
    /current
    0.19
    á»ĩ
    0.18
    itarian
    0.18
    ITIZE
    0.18
    /post
    0.18
    itizer
    0.17
    Act Density 0.011%

    No Known Activations