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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ani
    -0.15
    enis
    -0.15
    intern
    -0.14
    /tutorial
    -0.14
    _DI
    -0.14
     conver
    -0.14
    OTS
    -0.14
     pent
    -0.14
     Tomb
    -0.14
     TBD
    -0.14
    POSITIVE LOGITS
    pect
    0.15
    tica
    0.15
    bery
    0.14
    SWEP
    0.14
    Directive
    0.14
    cken
    0.14
    ocity
    0.14
    ystack
    0.14
    odash
    0.13
    ligt
    0.13
    Act Density 0.336%

    No Known Activations