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

    Neuronpedia

    INDEX
    Explanations

    references to retrospective reflections and realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToWorld
    -0.18
    enschaft
    -0.15
    ivot
    -0.15
    atak
    -0.15
    onte
    -0.14
    -pocket
    -0.14
    erap
    -0.14
     fed
    -0.14
    _feed
    -0.14
    onta
    -0.14
    POSITIVE LOGITS
    leanup
    0.19
     hindsight
    0.17
    TL
    0.16
    anca
    0.16
    ager
    0.16
    447
    0.16
    indsight
    0.15
    izers
    0.15
    ITU
    0.15
    stown
    0.15
    Act Density 0.257%

    No Known Activations