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

    Neuronpedia

    INDEX
    Explanations

    hints or mentions of future events or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    references to foreshadowing or indications of future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rior
    -0.71
    nea
    -0.70
    lux
    -0.70
    artney
    -0.68
    fare
    -0.68
    ÄŁ
    -0.67
    portion
    -0.65
    miah
    -0.65
    vict
    -0.64
    exper
    -0.64
    POSITIVE LOGITS
     hint
    1.36
     hints
    1.24
     clue
    1.01
     clues
    0.93
     hinted
    0.85
     glimps
    0.84
     wink
    0.77
    ibly
    0.76
    posts
    0.74
     warning
    0.71
    Act Density 0.054%

    No Known Activations