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

    Neuronpedia

    INDEX
    Explanations

    terms related to metrics and evaluation in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibly
    -0.18
    achu
    -0.16
    zcze
    -0.16
    ÃŃcÃŃ
    -0.15
    elivery
    -0.14
    rende
    -0.14
    ira
    -0.14
    олом
    -0.14
    ieber
    -0.14
    iginal
    -0.14
    POSITIVE LOGITS
    unsqueeze
    0.16
    ulings
    0.15
     Stick
    0.14
     Gap
    0.14
    ahlen
    0.14
    ÃĴ
    0.14
    stick
    0.14
     Foot
    0.13
    ût
    0.13
     Roo
    0.13
    Act Density 0.209%

    No Known Activations