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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _atomic
    -0.18
    uel
    -0.18
    ise
    -0.15
    omet
    -0.15
    ucc
    -0.15
    OLON
    -0.15
     multis
    -0.15
     Overrides
    -0.15
    encer
    -0.14
    cape
    -0.14
    POSITIVE LOGITS
    plier
    0.16
    pNet
    0.16
    paces
    0.15
    phem
    0.14
    gars
    0.14
    ále
    0.14
    astes
    0.14
    PFN
    0.14
    ocide
    0.13
    ieee
    0.13
    Act Density 0.054%

    No Known Activations