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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the purpose or aim of various topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.16
    istrovstvÃŃ
    -0.15
    ta
    -0.14
    ask
    -0.14
     Mask
    -0.14
    pas
    -0.14
    ãĥ³ãĤ°
    -0.14
    utf
    -0.14
    igu
    -0.13
     Hin
    -0.13
    POSITIVE LOGITS
    469
    0.15
    .Suppress
    0.15
    759
    0.15
    756
    0.14
    urgeon
    0.14
    èī¯
    0.14
    interop
    0.14
    Ïģα
    0.14
    licer
    0.14
    ingham
    0.14
    Act Density 0.075%

    No Known Activations