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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "What if"

    oai_token-act-pair · gpt-3.5-turbo

    instances of hypothetical scenarios or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eye
    -0.67
    abre
    -0.66
    ila
    -0.64
    ================================================================
    -0.64
    hands
    -0.63
    akia
    -0.63
    gae
    -0.62
    horse
    -0.62
    arm
    -0.61
     depths
    -0.60
    POSITIVE LOGITS
     someday
    0.84
     you
    0.80
    fy
    0.75
     they
    0.74
     somebody
    0.73
     someone
    0.72
    ?]
    0.70
     we
    0.69
     Gutenberg
    0.68
     hypot
    0.67
    Act Density 0.030%

    No Known Activations