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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or lack of confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onto
    -0.17
    ardo
    -0.15
    omez
    -0.15
    uele
    -0.14
    ono
    -0.14
    iens
    -0.14
    ALS
    -0.14
    orra
    -0.14
    жÑĥ
    -0.14
    PEED
    -0.14
    POSITIVE LOGITS
     about
    0.21
     whether
    0.17
    about
    0.17
    ipel
    0.16
    etched
    0.16
    باش
    0.15
    .syntax
    0.15
    ties
    0.15
     ML
    0.15
    ank
    0.15
    Act Density 0.039%

    No Known Activations