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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses that include the word "before"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or events occurring prior to a specific time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hack
    -0.78
    olog
    -0.69
    Die
    -0.67
    Goal
    -0.66
    oret
    -0.65
    amount
    -0.65
    aren
    -0.63
    DC
    -0.62
    urg
    -0.60
    expression
    -0.60
    POSITIVE LOGITS
    etheless
    0.81
    NetMessage
    0.80
     sunset
    0.77
     realizing
    0.73
    vernment
    0.72
     fading
    0.71
     retiring
    0.70
    lihood
    0.70
     sunrise
    0.67
     embark
    0.67
    Act Density 0.037%

    No Known Activations