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

    Neuronpedia

    INDEX
    Explanations

    references to data formatting and its various specifications or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    house
    -0.22
    hood
    -0.20
    han
    -0.18
    er
    -0.18
    har
    -0.18
    haven
    -0.18
    erman
    -0.17
    hot
    -0.17
    hus
    -0.17
    hook
    -0.17
    POSITIVE LOGITS
    ting
    0.42
    ted
    0.33
    TING
    0.25
    ters
    0.23
    td
    0.23
    tempt
    0.23
    te
    0.21
    unately
    0.21
    TERS
    0.21
    tingham
    0.21
    Act Density 0.012%

    No Known Activations