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

    Neuronpedia

    INDEX
    Explanations

    numerical values and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hire
    -0.18
    /tcp
    -0.16
    dzi
    -0.15
    illac
    -0.14
    hydrate
    -0.14
    /REC
    -0.14
    dü
    -0.13
    ìŀ¬
    -0.13
     Unt
    -0.13
    olet
    -0.13
    POSITIVE LOGITS
     жÑĥÑĢн
    0.17
     ÑģоÑģÑĤ
    0.16
     perg
    0.15
    ouz
    0.15
     Proble
    0.15
     Hoffman
    0.14
    acus
    0.14
     Gos
    0.14
    Ł
    0.14
     fare
    0.14
    Act Density 0.046%

    No Known Activations