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

    Neuronpedia

    INDEX
    Explanations

    decimal representations or numerical identifiers, often associated with coding or categorizing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sie
    -0.18
    lich
    -0.16
    ye
    -0.15
     ded
    -0.15
    lash
    -0.14
     Pearce
    -0.14
    527
    -0.14
    las
    -0.14
     mole
    -0.14
    avenport
    -0.14
    POSITIVE LOGITS
    ums
    0.16
    _named
    0.15
    haul
    0.15
    esz
    0.15
     honey
    0.15
    ivos
    0.15
    è¡Ľ
    0.14
    [$_
    0.14
    aturas
    0.14
    ipop
    0.14
    Act Density 0.068%

    No Known Activations