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

    Neuronpedia

    INDEX
    Explanations

    sequences with alternating letters and numbers or symbols

    oai_token-act-pair · gpt-3.5-turbo

    verb forms and modal verbs indicating desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -1.11
    paces
    -0.78
    abouts
    -0.74
    aday
    -0.64
    anke
    -0.63
    ema
    -0.62
    ktop
    -0.60
    ername
    -0.60
    heet
    -0.58
    tk
    -0.58
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.69
    voy
    0.69
    Lear
    0.68
    arta
    0.67
    ë
    0.66
    ³³³
    0.64
     Norn
    0.62
     âĶľ
    0.61
    BuyableInstoreAndOnline
    0.61
     constitu
    0.61
    Act Density 0.285%

    No Known Activations