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

    Neuronpedia

    INDEX
    Explanations

    the start of new text sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Weblinks
    -0.67
    pax
    -0.64
    路
    -0.63
    qos
    -0.63
    OfBirth
    -0.61
     Jacob
    -0.61
     Pax
    -0.61
    Pageable
    -0.61
    <s>
    -0.61
    ings
    -0.60
    POSITIVE LOGITS
    ••
    1.51
    ••••
    1.30
    •••
    1.23
    .•
    1.21
    er
    1.20
    °•
    1.14
    ~•
    1.06
     ••
    0.97
    ETHING
    0.96
     •
    0.92
    Act Density 0.119%

    No Known Activations