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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases emphasizing the concept of "fact" or factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acht
    -0.14
    ULD
    -0.14
    cope
    -0.14
     stakes
    -0.14
    ates
    -0.13
    feld
    -0.13
     Alb
    -0.13
    lop
    -0.13
     addition
    -0.13
     express
    -0.13
    POSITIVE LOGITS
    itious
    0.22
     fact
    0.20
    ually
    0.20
    uality
    0.19
    avana
    0.17
    amarin
    0.16
    aval
    0.16
    ories
    0.16
     Fact
    0.16
    urb
    0.15
    Act Density 0.016%

    No Known Activations