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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ήÏĤ
    -0.16
    stal
    -0.15
    quel
    -0.15
    ita
    -0.15
    ery
    -0.15
    ji
    -0.14
    nie
    -0.14
    ardon
    -0.14
    stalk
    -0.14
    acea
    -0.14
    POSITIVE LOGITS
    uther
    0.16
    ascar
    0.16
    amt
    0.16
    ìĦľëĬĶ
    0.14
    obao
    0.14
    mazon
    0.14
    onomous
    0.14
    735
    0.14
    weights
    0.14
    ndef
    0.14
    Act Density 0.036%

    No Known Activations