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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific points in time or periods

    oai_token-act-pair · gpt-3.5-turbo

    the presence of end-of-text tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornings
    -0.59
    emale
    -0.59
    herer
    -0.58
     beforehand
    -0.56
    *.
    -0.55
    /"
    -0.53
     afterwards
    -0.53
    ÃĥÃĤ
    -0.52
     conclud
    -0.52
     theirs
    -0.52
    POSITIVE LOGITS
     same
    0.77
    oret
    0.74
    resa
    0.73
     simplest
    0.73
     hottest
    0.72
     latest
    0.71
     following
    0.70
     largest
    0.70
     foregoing
    0.70
    ses
    0.70
    Act Density 0.918%

    No Known Activations