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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain conjunctions and prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forth
    -0.16
    ledge
    -0.15
    UPPORTED
    -0.14
    hoff
    -0.13
    meli
    -0.13
    istik
    -0.13
    gli
    -0.13
    quare
    -0.13
    /uploads
    -0.13
     зак
    -0.13
    POSITIVE LOGITS
    /or
    0.20
    /of
    0.17
     amp
    0.17
    rea
    0.15
    ÑĢониÑĩеÑģ
    0.15
    λÏī
    0.14
    rade
    0.14
    ehir
    0.14
    rov
    0.14
    osph
    0.14
    Act Density 0.053%

    No Known Activations