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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "turn" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dro
    -0.16
    zer
    -0.16
    oop
    -0.15
    layıcı
    -0.14
    yers
    -0.14
    lum
    -0.14
    rone
    -0.14
    _Inter
    -0.14
    ually
    -0.14
    layan
    -0.14
    POSITIVE LOGITS
    pike
    0.35
    stile
    0.29
    tables
    0.25
    ips
    0.22
    moil
    0.22
    igy
    0.21
    tabl
    0.21
    iej
    0.20
    about
    0.20
    itin
    0.20
    Act Density 0.011%

    No Known Activations