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

    Neuronpedia

    INDEX
    Explanations

    conditionals and dependencies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Král
    -0.15
    istar
    -0.15
     STAT
    -0.15
    HEST
    -0.14
    atra
    -0.14
     Stat
    -0.14
    ork
    -0.14
     çł
    -0.14
    ElementsBy
    -0.14
    ebin
    -0.14
    POSITIVE LOGITS
     ali
    0.17
    yor
    0.15
    efon
    0.14
    igne
    0.14
    Ali
    0.14
    Vel
    0.14
     tslib
    0.14
     Ali
    0.13
     ing
    0.13
    emy
    0.13
    Act Density 0.228%

    No Known Activations