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

    Neuronpedia

    INDEX
    Explanations

    references to placement opportunities or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ht
    -0.16
    allah
    -0.15
    awn
    -0.15
    fly
    -0.15
    atori
    -0.15
     nackte
    -0.14
    лаÑĩ
    -0.14
    atory
    -0.14
    áh
    -0.14
    oley
    -0.14
    POSITIVE LOGITS
    prot
    0.17
    #ac
    0.16
    teki
    0.14
     Extras
    0.14
    lbrace
    0.14
    ailles
    0.14
    leine
    0.14
    uste
    0.14
    Extras
    0.14
    letion
    0.14
    Act Density 0.003%

    No Known Activations