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

    Neuronpedia

    INDEX
    Explanations

    terms related to iteration and iterative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.19
    uron
    -0.17
    smith
    -0.16
    sWith
    -0.16
    igned
    -0.16
    ses
    -0.16
    lett
    -0.15
    ness
    -0.15
    sg
    -0.15
    sel
    -0.15
    POSITIVE LOGITS
    ative
    0.24
    atively
    0.23
    ally
    0.21
    аÑĤив
    0.19
    ationally
    0.17
    ALLY
    0.16
    acyj
    0.15
    uated
    0.15
    .hasNext
    0.15
    zzo
    0.15
    Act Density 0.012%

    No Known Activations