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

    Neuronpedia

    INDEX
    Explanations

    frequently mentioned statements or repeated phrases in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.58
     itſelf
    -0.54
    CreateModel
    -0.50
    ATN
    -0.50
    OrNil
    -0.48
     paramString
    -0.48
    rizona
    -0.48
    IContainer
    -0.47
    ſelf
    -0.45
    synthesize
    -0.45
    POSITIVE LOGITS
     frequently
    0.96
    frequently
    0.84
     frequent
    0.81
     regularly
    0.81
     frecuentemente
    0.78
     often
    0.75
    经常
    0.75
     Regularly
    0.73
     frequentemente
    0.73
    frequent
    0.71
    Act Density 0.494%

    No Known Activations