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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software programming exceptions

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'L' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chunks
    -0.66
     pops
    -0.63
     bursts
    -0.61
     touches
    -0.60
     curls
    -0.60
     drops
    -0.59
     scraps
    -0.59
     shocks
    -0.59
     leaps
    -0.58
     disappears
    -0.58
    POSITIVE LOGITS
     ourselves
    1.12
    re
    1.00
    have
    0.98
    ll
    0.97
    want
    0.94
    rely
    0.94
    athered
    0.93
    we
    0.92
    rer
    0.91
    agree
    0.91
    Act Density 0.087%

    No Known Activations