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

    Neuronpedia

    INDEX
    Explanations

    terms indicating strictness or parameters related to stringent criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.64
    Rptr
    -0.56
    Carriera
    -0.56
    jooq
    -0.52
    bkz
    -0.52
    ngdoc
    -0.51
     utafitiHapana
    -0.50
     merve
    -0.49
     للمعارف
    -0.49
     CreateTagHelper
    -0.48
    POSITIVE LOGITS
    ua
    0.83
    UA
    0.70
     strict
    0.61
    itz
    0.56
    uan
    0.54
     Strict
    0.53
    omitempty
    0.52
     bleed
    0.50
    Strict
    0.50
    ITZ
    0.49
    Act Density 0.344%

    No Known Activations