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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or conditionality, particularly in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geb
    -0.17
     -
    -0.15
    orgia
    -0.15
    -
    -0.15
    RS
    -0.14
    jab
    -0.14
    x
    -0.13
    ales
    -0.13
    FT
    -0.13
    vice
    -0.13
    POSITIVE LOGITS
     but
    0.22
     nhÆ°ng
    0.17
    arella
    0.17
    اÙĨÙĪ
    0.16
    깨
    0.16
     âĹĦ
    0.16
    aber
    0.15
    AREST
    0.15
     но
    0.15
    but
    0.15
    Act Density 0.214%

    No Known Activations