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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the identity or description of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertz
    -0.16
    /gui
    -0.15
    gnu
    -0.15
    ighter
    -0.15
    aversable
    -0.15
    udic
    -0.15
    erton
    -0.14
    idal
    -0.14
    irit
    -0.14
    esser
    -0.14
    POSITIVE LOGITS
    liers
    0.16
    dn
    0.16
    lies
    0.15
    _compat
    0.15
    mini
    0.15
    otti
    0.15
    seau
    0.14
     Fat
    0.14
     Hass
    0.14
    ji
    0.14
    Act Density 0.015%

    No Known Activations