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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.47
    atra
    -0.46
    oléon
    -0.46
     break
    -0.45
    g
    -0.45
    postas
    -0.45
    したもの
    -0.44
    tomos
    -0.43
    žky
    -0.43
     Pi
    -0.43
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.76
    rizona
    0.64
     purpoſe
    0.62
    AndEndTag
    0.61
     NDEBUG
    0.60
    ]")]
    0.59
    uegos
    0.57
     doubtnut
    0.57
     myſelf
    0.56
    oa̍t
    0.55
    Act Density 0.332%

    No Known Activations