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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical terms and concepts in various fields

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "with"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.80
    matter
    -0.77
    TG
    -0.76
    USE
    -0.70
    Reuters
    -0.68
    BU
    -0.68
    kind
    -0.67
    ulet
    -0.67
    Ess
    -0.66
    chan
    -0.65
    POSITIVE LOGITS
    stood
    1.64
     regard
    1.19
    drawn
    1.17
     respect
    1.14
     regards
    1.13
    draw
    1.09
     minimal
    1.00
     lots
    0.99
     attendant
    0.99
     varying
    0.99
    Act Density 0.139%

    No Known Activations