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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lin
    -0.14
     Neighbor
    -0.14
    ansa
    -0.14
    ym
    -0.14
    каз
    -0.13
    etic
    -0.13
    okens
    -0.13
     Fees
    -0.13
     Direct
    -0.13
    åŃĿ
    -0.13
    POSITIVE LOGITS
    ioni
    0.17
    hci
    0.15
    ,[],
    0.15
    alist
    0.15
    enie
    0.15
    untime
    0.14
    532
    0.14
    iloc
    0.14
     Caucasian
    0.14
     briefing
    0.14
    Act Density 0.011%

    No Known Activations