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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĹ
    -0.16
    ilos
    -0.16
    arda
    -0.16
    äºľ
    -0.15
    umen
    -0.15
    aines
    -0.15
    illez
    -0.15
    cla
    -0.14
    ughters
    -0.14
    alem
    -0.14
    POSITIVE LOGITS
    emer
    0.17
    errated
    0.16
    .datab
    0.15
    -flag
    0.15
    epad
    0.15
    uest
    0.14
    ration
    0.14
    ocket
    0.14
    ally
    0.14
    raman
    0.14
    Act Density 0.098%

    No Known Activations