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

    Neuronpedia

    INDEX
    Explanations

    words involving the concept of interleaving

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "sp" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.71
    assetsadobe
    -0.68
    vironment
    -0.68
    ãĥĥãĥĪ
    -0.67
     behold
    -0.65
    obyl
    -0.64
     anticipation
    -0.64
    naissance
    -0.63
     contraceptive
    -0.62
    sbm
    -0.62
    POSITIVE LOGITS
    iral
    1.06
    atial
    1.04
    acer
    1.00
    aghetti
    0.99
    iegel
    0.98
    urred
    0.94
    acious
    0.93
    encer
    0.93
    inn
    0.92
    okes
    0.91
    Act Density 0.011%

    No Known Activations