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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the importance of noting or mentioning specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ount
    -0.16
    ISR
    -0.14
    visor
    -0.14
    assi
    -0.14
    ặn
    -0.13
     elect
    -0.13
    /in
    -0.13
    likle
    -0.13
    affles
    -0.13
     âĻ¥
    -0.13
    POSITIVE LOGITS
     note
    0.23
    note
    0.21
    Note
    0.17
     Note
    0.17
     notes
    0.16
    96
    0.16
    -note
    0.16
    주ìĿĺ
    0.15
    dob
    0.15
    áŀ¶
    0.15
    Act Density 0.060%

    No Known Activations