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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the presence of a "fact" or assert statements about reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryn
    -0.16
    nte
    -0.16
    ensis
    -0.15
    ILLISE
    -0.15
    ould
    -0.14
    еÑĢеÑĩ
    -0.14
    nek
    -0.13
    ILON
    -0.13
    thus
    -0.13
    룬
    -0.13
    POSITIVE LOGITS
     fact
    0.21
    itious
    0.20
    uality
    0.18
    ually
    0.16
    arding
    0.15
    zik
    0.14
    fact
    0.14
    annel
    0.13
    umas
    0.13
    dehy
    0.13
    Act Density 0.021%

    No Known Activations