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

    Neuronpedia

    INDEX
    Explanations

    references to characters and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xia
    -0.16
    dh
    -0.16
    ehr
    -0.15
    dum
    -0.15
    iros
    -0.14
    unsch
    -0.14
    znik
    -0.14
    ez
    -0.14
    dorf
    -0.14
    ensch
    -0.14
    POSITIVE LOGITS
     canon
    0.15
    lak
    0.15
    las
    0.14
    /tiny
    0.14
    кин
    0.13
     Canon
    0.13
     Diaz
    0.13
    ROP
    0.13
    åĴ²
    0.13
    eds
    0.13
    Act Density 0.361%

    No Known Activations