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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating intentions or actions related to future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.17
    par
    -0.14
    ink
    -0.14
    raquo
    -0.14
    aul
    -0.14
    pet
    -0.13
    lej
    -0.13
    plor
    -0.13
    ders
    -0.13
    alone
    -0.13
    POSITIVE LOGITS
    ishi
    0.17
    linger
    0.16
    cil
    0.16
    ijing
    0.16
    inyin
    0.16
    ettle
    0.16
    uela
    0.15
    orch
    0.14
    lient
    0.14
    get
    0.14
    Act Density 0.065%

    No Known Activations