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

    Neuronpedia

    INDEX
    Explanations

    references to evaluation and recognition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hra
    -0.18
     note
    -0.14
    insi
    -0.14
    ior
    -0.14
    ens
    -0.14
    asca
    -0.14
    cht
    -0.14
     echo
    -0.14
    eton
    -0.14
    rette
    -0.13
    POSITIVE LOGITS
    구
    0.16
     eigentlich
    0.15
    arend
    0.14
     ìŀĦ
    0.14
    agoon
    0.14
    arena
    0.14
    icie
    0.14
     indeed
    0.14
    donnees
    0.13
    arkan
    0.13
    Act Density 0.705%

    No Known Activations