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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation that indicate structure within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.82
     Anſ
    -0.81
     purpoſe
    -0.79
     Monfieur
    -0.76
     ecosystem
    -0.75
    ategor
    -0.74
     impact
    -0.74
     Conſ
    -0.74
     ecosystems
    -0.73
     overall
    -0.73
    POSITIVE LOGITS
    AndEndTag
    1.00
     skall
    0.84
     '\\;'
    0.82
     rospy
    0.79
    SBATCH
    0.73
    disposing
    0.69
    ตร์
    0.69
     CreateTagHelper
    0.69
    ]")]
    0.68
    WritableDatabase
    0.68
    Act Density 0.554%

    No Known Activations