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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries regarding the nature of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.17
    mers
    -0.17
    æ´²
    -0.17
    uent
    -0.15
    .scalablytyped
    -0.15
    /black
    -0.15
    dyn
    -0.14
    ueba
    -0.14
    unya
    -0.14
    net
    -0.13
    POSITIVE LOGITS
     otherwise
    0.19
    .cd
    0.18
    oping
    0.18
    -ÑĤо
    0.18
    lea
    0.16
    -либо
    0.16
     we
    0.16
     else
    0.16
     is
    0.15
    ley
    0.15
    Act Density 0.084%

    No Known Activations