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

    Neuronpedia

    INDEX
    Explanations

    references to the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anko
    -0.19
    ears
    -0.18
    owski
    -0.17
    rowse
    -0.16
    nett
    -0.16
    CTIONS
    -0.14
    olver
    -0.14
    ummer
    -0.14
    andom
    -0.14
    ató
    -0.14
    POSITIVE LOGITS
    ÑģÑĤе
    0.15
    uess
    0.14
    iner
    0.14
    acic
    0.14
    зв
    0.14
     ÏĦι
    0.13
    imli
    0.13
    ivan
    0.13
     NOTIFY
    0.13
    ij¸
    0.13
    Act Density 0.008%

    No Known Activations