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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dialogue indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oen
    -0.16
    org
    -0.15
    urar
    -0.15
    aya
    -0.15
    ui
    -0.14
    idue
    -0.14
    ä½ķ
    -0.13
     бли
    -0.13
    ģm
    -0.13
     Licht
    -0.13
    POSITIVE LOGITS
    ossa
    0.14
    kap
    0.14
    etry
    0.14
    ndl
    0.14
    ÙĬÙĥÙĬ
    0.14
    ials
    0.13
    ilion
    0.13
    ORY
    0.13
     handleClick
    0.13
    .sharedInstance
    0.13
    Act Density 0.005%

    No Known Activations