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

    Neuronpedia

    INDEX
    Explanations

    references to links or URLs within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    353
    -0.15
    whel
    -0.14
    UNK
    -0.14
    337
    -0.14
     Colonial
    -0.13
     pill
    -0.13
    oyer
    -0.13
    unks
    -0.13
    zz
    -0.13
    zos
    -0.13
    POSITIVE LOGITS
     Sed
    0.16
    istrovstvÃŃ
    0.16
    ÑĢож
    0.16
    tim
    0.15
     klu
    0.15
    ounder
    0.15
     fused
    0.14
    /chart
    0.14
    ìĽĶë¶ĢíĦ°
    0.14
    eldorf
    0.14
    Act Density 0.002%

    No Known Activations