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

    Neuronpedia

    INDEX
    Explanations

    phrases or collocations where something is no longer relevant or obsolete

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of "things from the past"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sshd
    -0.71
    baugh
    -0.64
    tub
    -0.63
     Revis
    -0.60
     Tanner
    -0.59
    oons
    -0.59
    clone
    -0.58
    auga
    -0.57
    Dash
    -0.57
    dot
    -0.55
    POSITIVE LOGITS
    icial
    0.88
     importance
    0.87
     utmost
    0.86
     theirs
    0.80
     significance
    0.78
     brilliance
    0.78
     beauty
    0.78
     prominence
    0.77
     integrity
    0.76
     ours
    0.76
    Act Density 0.092%

    No Known Activations