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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions using specific numbers and operators

    oai_token-act-pair · gpt-3.5-turbo

    mathematical terms and operations in the context of numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conom
    -0.79
    Executive
    -0.74
    Website
    -0.72
    erv
    -0.70
    BIL
    -0.69
    inflamm
    -0.64
    WARE
    -0.63
    Skin
    -0.62
    Social
    -0.61
    comed
    -0.61
    POSITIVE LOGITS
     infinity
    1.22
     nil
    1.07
     zero
    1.03
     <=
    0.96
     0
    0.95
     ½
    0.94
     -=
    0.92
     {}
    0.92
     multiplication
    0.91
     decimal
    0.91
    Act Density 0.150%

    No Known Activations