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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions of loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yla
    -0.15
     Alb
    -0.15
    ookie
    -0.15
     bod
    -0.15
    uct
    -0.15
     Duc
    -0.15
    inkel
    -0.14
    uly
    -0.14
    abit
    -0.14
    ,
    -0.14
    POSITIVE LOGITS
     Saunders
    0.17
    .sponge
    0.16
    uppen
    0.16
     addCriterion
    0.16
    -toggler
    0.15
    ën
    0.15
    볨
    0.14
    .scalablytyped
    0.14
    ÑĢог
    0.14
    _VM
    0.14
    Act Density 0.027%

    No Known Activations