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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methods and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.85
    Autoritní
    -0.78
    SOUNDBITE
    -0.75
     houſe
    -0.74
     themſelves
    -0.71
     ſtate
    -0.71
     незавершена
    -0.70
     itſelf
    -0.70
    /**
    -0.69
    ˏ
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.57
     مشين
    0.53
    ↵↵↵↵
    0.47
    Or
    0.46
    Personendaten
    0.46
    ↵↵↵
    0.46
    thâu
    0.45
    。「
    0.44
    ).
    0.43
    ↵↵↵↵↵↵
    0.43
    Act Density 0.710%

    No Known Activations