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

    Neuronpedia

    INDEX
    Explanations

    key names and numerical values indicating performance metrics or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     however
    -0.74
    however
    -0.74
     porém
    -0.68
    tvguidetime
    -0.67
    However
    -0.67
     and
    -0.64
    хьтан
    -0.64
     însă
    -0.64
     però
    -0.63
     However
    -0.63
    POSITIVE LOGITS
     dermed
    0.63
     thereof
    0.63
     consequently
    0.62
    Enllaces
    0.60
     frankly
    0.60
     therein
    0.58
     accordingly
    0.57
    何より
    0.56
     therefor
    0.55
     daarbij
    0.54
    Act Density 1.272%

    No Known Activations