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

    Neuronpedia

    INDEX
    Explanations

    terms related to negative or problematic situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    辦
    -0.16
    ãĥĨãĥ«
    -0.15
     Ri
    -0.15
    asl
    -0.14
    counts
    -0.14
    ãĥ£
    -0.14
    aksi
    -0.14
    æı
    -0.14
    ä¼Ļ
    -0.14
    Ħìŀ¬
    -0.14
    POSITIVE LOGITS
    ably
    0.17
    /un
    0.16
    rous
    0.16
    eneg
    0.15
    /in
    0.15
    /il
    0.14
    ky
    0.14
    ilo
    0.14
    ly
    0.14
    ilib
    0.14
    Act Density 0.106%

    No Known Activations