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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovu
    -0.16
    ppe
    -0.15
    vyk
    -0.15
    agner
    -0.14
    uld
    -0.14
    gmt
    -0.14
     hist
    -0.14
    à¤Ĺर
    -0.14
    inth
    -0.14
    обÑĢаз
    -0.13
    POSITIVE LOGITS
    ´
    0.16
    attice
    0.15
    resse
    0.15
    /xhtml
    0.15
    _fence
    0.14
     !=↵
    0.14
    dle
    0.14
    æĭ©
    0.14
    .foundation
    0.14
    rab
    0.13
    Act Density 0.054%

    No Known Activations