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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    numeric output and computations related to statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    license
    -0.78
     grassroots
    -0.77
     Ivanka
    -0.70
    assion
    -0.68
     welcoming
    -0.67
     Thailand
    -0.66
     celebr
    -0.65
     diplomatic
    -0.64
    licensed
    -0.64
     fostering
    -0.63
    POSITIVE LOGITS
     \(
    1.13
     \(\
    1.11
    orem
    1.04
     subtract
    1.03
     interpol
    0.98
     ÎĶ
    0.98
     $\
    0.94
     computed
    0.94
     integers
    0.92
     algebra
    0.91
    Act Density 1.025%

    No Known Activations