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

    Neuronpedia

    INDEX
    Explanations

    terminology related to axioms and their variations in scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    亮
    -0.19
    occo
    -0.18
    acey
    -0.18
    ancock
    -0.17
    uffs
    -0.17
    erset
    -0.17
    aste
    -0.16
    ajar
    -0.16
    utschen
    -0.15
    askell
    -0.15
    POSITIVE LOGITS
    ioms
    0.32
    illary
    0.31
    ially
    0.28
    minster
    0.27
    cess
    0.25
    onal
    0.24
    elsen
    0.23
    les
    0.21
    pert
    0.21
    eman
    0.21
    Act Density 0.012%

    No Known Activations