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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'p' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arent
    -0.17
     pant
    -0.16
    KA
    -0.16
    ose
    -0.15
    sis
    -0.15
    ending
    -0.15
    SP
    -0.15
    ifton
    -0.15
    si
    -0.15
     vanity
    -0.15
    POSITIVE LOGITS
    esto
    0.23
    ears
    0.21
    imiento
    0.19
    ome
    0.19
    еÑģÑĤо
    0.18
    anko
    0.18
     ast
    0.18
    umper
    0.17
    ean
    0.17
    imento
    0.17
    Act Density 0.010%

    No Known Activations