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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate personal experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buat
    -0.16
    chyb
    -0.15
    agne
    -0.15
    foundland
    -0.14
    riere
    -0.14
    iny
    -0.14
    ãĤ±ãĥĥãĥĪ
    -0.14
    tdown
    -0.14
    irket
    -0.14
    INCLUDE
    -0.13
    POSITIVE LOGITS
     sometimes
    0.18
     ÑĤам
    0.18
    éĤ£éĩĮ
    0.17
     there
    0.15
    reve
    0.15
    ona
    0.14
    218
    0.14
     theirs
    0.14
    inger
    0.14
    xx
    0.14
    Act Density 0.013%

    No Known Activations