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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.18
    inode
    -0.16
    rung
    -0.14
    ÑĩаÑģÑĤ
    -0.14
    Wnd
    -0.14
    hots
    -0.14
    _currency
    -0.14
    oya
    -0.13
     Rug
    -0.13
    iph
    -0.13
    POSITIVE LOGITS
     Sound
    0.15
    úc
    0.15
     Grimm
    0.15
    andro
    0.14
     Ott
    0.14
     Doe
    0.14
    upa
    0.13
    nal
    0.13
    unnable
    0.13
     Mus
    0.13
    Act Density 0.110%

    No Known Activations