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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTA
    -0.15
     htons
    -0.14
    graduate
    -0.14
    byname
    -0.14
    ASSERT
    -0.14
    ITT
    -0.14
     backyard
    -0.13
    ãĢħ
    -0.13
    ync
    -0.13
    uer
    -0.13
    POSITIVE LOGITS
     go
    0.21
     sits
    0.20
     sit
    0.19
     GO
    0.19
     goes
    0.19
    gos
    0.18
     finally
    0.16
    opsis
    0.15
     Go
    0.15
     lies
    0.15
    Act Density 0.019%

    No Known Activations