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

    Neuronpedia

    INDEX
    Explanations

    references to shifts in paradigms across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onse
    -0.15
     latter
    -0.15
    argas
    -0.15
    ir
    -0.14
    is
    -0.14
    ẩu
    -0.14
     Duncan
    -0.14
     armored
    -0.14
    iler
    -0.13
    tie
    -0.13
    POSITIVE LOGITS
    rrha
    0.20
    QUEST
    0.15
    pend
    0.15
    kelig
    0.15
    abwe
    0.14
    avicon
    0.14
    ÏĢα
    0.14
    pei
    0.14
    TEGER
    0.14
    avit
    0.14
    Act Density 0.006%

    No Known Activations