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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to ranking or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Graz
    -0.16
    ez
    -0.14
    tom
    -0.13
     Ùģار
    -0.13
    ichert
    -0.13
    iges
    -0.13
     Lambert
    -0.13
    ly
    -0.13
     дол
    -0.13
    kehr
    -0.13
    POSITIVE LOGITS
    Ī
    0.15
    sian
    0.14
    iology
    0.14
    éry
    0.14
    271
    0.14
    olicited
    0.14
    illac
    0.14
    CLU
    0.14
    OOM
    0.14
    alc
    0.14
    Act Density 0.214%

    No Known Activations