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

    Neuronpedia

    INDEX
    Explanations

    instructions or actions related to performing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.56
     abſ
    -0.53
    randomUUID
    -0.52
    parsedMessage
    -0.50
     anſ
    -0.50
     unſ
    -0.48
     Schwartz
    -0.47
     ſta
    -0.47
     <<<<<<<<<<<<<<
    -0.47
     Whitfield
    -0.47
    POSITIVE LOGITS
    Doing
    1.05
    doing
    1.04
     Doing
    1.01
     doing
    0.99
     DOING
    0.89
     do
    0.85
     done
    0.80
     doings
    0.75
     Done
    0.72
     doin
    0.70
    Act Density 0.209%

    No Known Activations