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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "bank" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEP
    -0.17
    лÑĥ
    -0.16
    ritz
    -0.15
    aneous
    -0.15
    antar
    -0.15
    atsby
    -0.15
    outu
    -0.14
    ÐĶÐļ
    -0.14
    /fw
    -0.14
    382
    -0.14
    POSITIVE LOGITS
    isco
    0.16
    ertest
    0.16
    iest
    0.16
    marked
    0.16
    .fm
    0.15
    cies
    0.15
    unter
    0.14
    ëĿ½
    0.14
    918
    0.14
    atest
    0.14
    Act Density 0.017%

    No Known Activations