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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    hypothetical scenarios or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.68
     cringe
    -0.65
     Beware
    -0.64
    atile
    -0.61
     provoke
    -0.61
    aina
    -0.60
    oris
    -0.58
    Ãį
    -0.58
    enos
    -0.57
     bru
    -0.57
    POSITIVE LOGITS
     hadn
    1.01
     weren
    0.94
     existed
    0.88
    Had
    0.88
     normalized
    0.85
     instead
    0.83
     were
    0.82
     stayed
    0.79
    hered
    0.78
     substituted
    0.77
    Act Density 0.255%

    No Known Activations