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

    Neuronpedia

    INDEX
    Explanations

    terms related to annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOCKS
    -0.18
    inja
    -0.17
    PAIR
    -0.16
    akash
    -0.15
    ··
    -0.15
    iju
    -0.14
    .gs
    -0.14
    _globals
    -0.14
    .dy
    -0.14
     jon
    -0.14
    POSITIVE LOGITS
    weise
    0.27
    weis
    0.24
     links
    0.15
    èij
    0.15
    hil
    0.15
     Rich
    0.15
    odka
    0.14
    mel
    0.14
    richt
    0.14
    lass
    0.14
    Act Density 0.005%

    No Known Activations