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

    Neuronpedia

    INDEX
    Explanations

    phrases that reflect cultural or religious significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ´Ī
    -0.14
    ICO
    -0.14
     DISCLAIMER
    -0.14
     Tmax
    -0.14
    abbo
    -0.14
    legg
    -0.14
    /tutorial
    -0.13
    opoulos
    -0.13
    antry
    -0.13
    çħ§
    -0.13
    POSITIVE LOGITS
     meaning
    0.36
     translated
    0.33
     literally
    0.33
    meaning
    0.30
    liter
    0.28
    translated
    0.27
     Meaning
    0.27
     literal
    0.26
     translates
    0.26
    rough
    0.26
    Act Density 0.133%

    No Known Activations