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

    Neuronpedia

    INDEX
    Explanations

    instances of online comments or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pend
    -0.15
    vet
    -0.15
    igos
    -0.14
    occo
    -0.13
    aret
    -0.13
    uest
    -0.13
     vet
    -0.13
     Carpet
    -0.13
     Mat
    -0.13
     coppia
    -0.13
    POSITIVE LOGITS
    ream
    0.16
    terdam
    0.16
    ayla
    0.15
    ihad
    0.15
    sta
    0.15
    isphere
    0.14
    머
    0.14
    zsche
    0.14
    ÑĢин
    0.14
    ittings
    0.14
    Act Density 0.099%

    No Known Activations