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

    Neuronpedia

    INDEX
    Explanations

    specific instructions or commands related to using technology like software tools and scripts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" and related usage instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mysteries
    -0.62
    Ń·
    -0.62
     behold
    -0.61
     nerv
    -0.61
     undertaking
    -0.61
    inois
    -0.60
     Bounty
    -0.57
     Buffett
    -0.56
     promulg
    -0.56
    cffffcc
    -0.56
    POSITIVE LOGITS
    fully
    1.15
    FUL
    1.10
    full
    1.02
    ful
    0.86
    fulness
    0.85
     sparing
    0.79
     tools
    0.79
     condoms
    0.76
     shortcuts
    0.74
     levers
    0.73
    Act Density 0.086%

    No Known Activations