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

    Neuronpedia

    INDEX
    Explanations

    number-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter 'N' in various contexts or usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cerberus
    -0.75
     horizont
    -0.70
    Ĥİ
    -0.69
     highs
    -0.67
     Thumbnails
    -0.66
     breeze
    -0.65
     Sparrow
    -0.64
     difficulty
    -0.63
     downed
    -0.62
     Vaj
    -0.62
    POSITIVE LOGITS
    uggets
    1.25
    erves
    1.18
    ucle
    1.15
    umerous
    1.15
    ameless
    1.14
    onsense
    1.13
    aughty
    1.11
    ihil
    1.11
    guyen
    1.09
    atalie
    1.08
    Act Density 0.036%

    No Known Activations