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

    Neuronpedia

    INDEX
    Explanations

    technical or academic formatting cues and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    円
    -0.60
    rmtree
    -0.51
    」
    -0.49
    gameserver
    -0.49
    ↵↵
    -0.49
    。
    -0.49
    ».
    -0.45
     abgerufen
    -0.44
    makeConstraints
    -0.43
    }
    -0.42
    POSITIVE LOGITS
    Демографія
    0.85
     whoſe
    0.82
    __(/*!
    0.79
    клопе
    0.78
     ostavi
    0.76
     purpoſe
    0.75
     becauſe
    0.74
     himſelf
    0.73
     raiſ
    0.72
     itſelf
    0.71
    Act Density 0.125%

    No Known Activations