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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions taking place

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrations or events related to new beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caveats
    -0.70
     hindsight
    -0.65
    earchers
    -0.61
     CBO
    -0.57
     caveat
    -0.56
     Carney
    -0.55
     economists
    -0.55
    ographers
    -0.54
    Story
    -0.54
     concedes
    -0.53
    POSITIVE LOGITS
     respectively
    0.84
    their
    0.82
     theirs
    0.74
    )).
    0.72
    !".
    0.63
     THEIR
    0.63
    ".
    0.62
     their
    0.61
    Ń·
    0.61
    %.
    0.60
    Act Density 1.593%

    No Known Activations