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

    Neuronpedia

    INDEX
    Explanations

    structured references related to variables and formats in programming or data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     canst
    -0.48
    发表于
    -0.48
    findpost
    -0.46
    WriteTagHelper
    -0.44
     userDao
    -0.44
     meriva
    -0.43
     Réponses
    -0.43
    wickshire
    -0.43
     profi
    -0.43
    jména
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.51
    ########.
    0.49
     pitié
    0.48
    قایناق‌لار
    0.45
     Roskov
    0.43
    AutoScaleMode
    0.41
     culprit
    0.40
     ProtoMessage
    0.40
     shocked
    0.39
     McAllister
    0.39
    Act Density 0.174%

    No Known Activations