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

    Neuronpedia

    INDEX
    Explanations

    references to data and evidence in academic or research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.65
    ])),
    -0.64
    >');
    -0.63
    }`).
    -0.60
    BeginInit
    -0.60
    "))
    -0.60
    ')))
    -0.59
    ')));
    -0.58
    expandindo
    -0.58
    '))
    -0.57
    POSITIVE LOGITS
    NUMX
    0.69
    devamını
    0.63
    mtrl
    0.60
    ſhip
    0.56
    ELTS
    0.56
    neſs
    0.56
     ويكيپيديا
    0.56
    ſelf
    0.55
     tearDown
    0.55
    دواج
    0.53
    Act Density 0.440%

    No Known Activations