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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific pattern related to "Pr" or "Praise"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipay
    -0.19
    baum
    -0.16
    elf
    -0.16
    885
    -0.15
    897
    -0.15
    liqu
    -0.14
    ationship
    -0.14
    blade
    -0.14
    endale
    -0.14
    ê³Ħ
    -0.14
    POSITIVE LOGITS
    chal
    0.18
    udence
    0.18
    zem
    0.17
    %f
    0.16
    /pr
    0.16
     Pr
    0.15
    zy
    0.15
    akash
    0.15
    erna
    0.15
    ullen
    0.15
    Act Density 0.022%

    No Known Activations