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

    Neuronpedia

    INDEX
    Explanations

    statements related to opinions or declarations made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »,
    -1.26
    ?",
    -1.26
    !",
    -1.25
    。」
    -1.23
    "],
    -1.23
    .",
    -1.21
    "),
    -1.21
    」，
    -1.20
    」
    -1.19
    "،
    -1.19
    POSITIVE LOGITS
     “
    2.03
     "
    1.57
     ''
    1.07
     ``
    1.06
     “...
    0.95
     ​
    0.69
     ...
    0.61
     “[
    0.60
     “¿
    0.59
     ‘‘
    0.58
    Act Density 0.267%

    No Known Activations