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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    numerical references or values related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hung
    -0.81
     swallowing
    -0.69
     guarding
    -0.67
     brav
    -0.67
     elevation
    -0.65
     wink
    -0.64
     hormones
    -0.64
     travers
    -0.64
     empt
    -0.64
    administ
    -0.63
    POSITIVE LOGITS
     SHARES
    1.04
    ertodd
    0.86
     NCT
    0.85
    maxwell
    0.82
    :{
    0.76
     ·
    0.75
     Expand
    0.75
    rd
    0.74
     Explicit
    0.73
    %:
    0.72
    Act Density 0.102%

    No Known Activations