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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oku
    -0.17
    WXYZ
    -0.16
    ohn
    -0.15
    æ´»
    -0.15
    ASA
    -0.14
    NF
    -0.14
    otu
    -0.14
    Hits
    -0.14
    еÑĢк
    -0.14
    utsch
    -0.14
    POSITIVE LOGITS
    icha
    0.16
     Ze
    0.15
    Äĩe
    0.15
    Ñģим
    0.14
    ym
    0.14
    tere
    0.14
    chrift
    0.14
     complexes
    0.14
    anness
    0.14
    lie
    0.14
    Act Density 0.001%

    No Known Activations