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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hints and clues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elijke
    -0.15
     addCriterion
    -0.15
    Ïĥον
    -0.14
    ูà¸ķ
    -0.14
    ongan
    -0.14
     migrationBuilder
    -0.13
    лÑĥб
    -0.13
    ÑģÑĮого
    -0.13
     suspected
    -0.13
     Pew
    -0.13
    POSITIVE LOGITS
    ingly
    0.18
     glimpse
    0.18
    uela
    0.17
     preview
    0.16
    291
    0.15
     Mun
    0.14
     Cho
    0.14
     hint
    0.14
    haar
    0.14
     grips
    0.14
    Act Density 0.052%

    No Known Activations