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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical limitations or impairments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bbe
    -0.16
    ieves
    -0.15
    кид
    -0.15
    plusplus
    -0.15
    cole
    -0.15
    دÛĮد
    -0.15
    mailto
    -0.14
    _lengths
    -0.14
    .wp
    -0.14
    amation
    -0.14
    POSITIVE LOGITS
    óm
    0.15
     imp
    0.14
    æ²
    0.14
    .Restr
    0.14
    arty
    0.14
    ottom
    0.14
     publication
    0.14
    ayet
    0.14
    784
    0.13
     going
    0.13
    Act Density 0.079%

    No Known Activations