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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to negative or harmful qualities

    oai_token-act-pair · gpt-3.5-turbo

    words related to senselessness or lack of meaning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.88
    ept
    -0.77
    ebus
    -0.73
    iola
    -0.71
    emis
    -0.70
     climates
    -0.70
    arte
    -0.69
    apter
    -0.68
    stanbul
    -0.67
    tta
    -0.67
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.90
     senseless
    0.87
    Ó
    0.73
    ãĥĻ
    0.68
    ãĥĥãĥī
    0.66
     repetition
    0.66
    \\\\\\\\
    0.65
    ãĥģ
    0.65
    Repe
    0.64
    aturally
    0.63
    Act Density 0.047%

    No Known Activations