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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "Tor" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izi
    -0.16
    irs
    -0.14
    OrFail
    -0.14
    enus
    -0.14
    InputElement
    -0.14
    kü
    -0.14
    ymes
    -0.14
    é¢ĺ
    -0.14
    arend
    -0.13
    otherwise
    -0.13
    POSITIVE LOGITS
    mented
    0.28
    rance
    0.24
    adol
    0.21
    oidal
    0.21
    rens
    0.20
    onto
    0.19
    reon
    0.19
    ment
    0.19
    rence
    0.19
    ments
    0.18
    Act Density 0.009%

    No Known Activations