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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rique
    -0.17
    βα
    -0.15
     Sunder
    -0.15
    agos
    -0.15
    iore
    -0.14
     паÑĢа
    -0.14
    tek
    -0.14
    aines
    -0.14
    king
    -0.14
    nez
    -0.14
    POSITIVE LOGITS
     other
    0.17
    idor
    0.17
    arters
    0.16
     algun
    0.15
     any
    0.15
    _aff
    0.15
    iment
    0.14
    çļĨ
    0.14
     something
    0.14
    ellite
    0.14
    Act Density 0.072%

    No Known Activations