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

    Neuronpedia

    INDEX
    Explanations

    high-frequency words or phrases that occur in the text

    oai_token-act-pair · gpt-3.5-turbo

    quantitative expressions and phrases related to approximation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IBLE
    -0.64
    dies
    -0.63
     bounty
    -0.62
    ailable
    -0.59
    senal
    -0.59
     CV
    -0.58
     debtor
    -0.57
     destination
    -0.56
     jo
    -0.56
     graveyard
    -0.55
    POSITIVE LOGITS
    entimes
    1.18
     importantly
    1.11
    withstanding
    0.91
    etheless
    0.89
     Ago
    0.86
    ortunately
    0.84
     surprisingly
    0.81
     unsurprisingly
    0.78
    ccording
    0.77
    surprisingly
    0.76
    Act Density 0.212%

    No Known Activations