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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords or terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gameplay and player involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.88
    OFF
    -0.77
    TAIN
    -0.77
    pmwiki
    -0.76
    STR
    -0.76
    ãĥ©ãĥ³
    -0.75
    Mount
    -0.73
    Camp
    -0.72
    Str
    -0.71
    prop
    -0.71
    POSITIVE LOGITS
    a
    0.82
     a
    0.77
     ace
    0.72
    aye
    0.70
     A
    0.66
     Nou
    0.64
     Ave
    0.64
     foo
    0.63
     Clyde
    0.63
     an
    0.62
    Act Density 0.184%

    No Known Activations