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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" indicating temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vik
    -0.16
    je
    -0.15
    _exports
    -0.14
    ιÏĥ
    -0.14
    лаÑģÑĤи
    -0.14
    thood
    -0.13
    Reflect
    -0.13
    azer
    -0.13
    ĽĦ
    -0.13
     sanct
    -0.13
    POSITIVE LOGITS
    оÑģÑĥд
    0.15
    rud
    0.14
    -нибÑĥдÑĮ
    0.14
    æĦŁæĥħ
    0.14
    igest
    0.13
    pty
    0.13
     Gregg
    0.13
    elve
    0.13
    glich
    0.13
     trá»±c
    0.13
    Act Density 0.046%

    No Known Activations