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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases that indicate location or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ideo
    -0.17
    fur
    -0.16
    ampo
    -0.16
    един
    -0.15
    759
    -0.15
    aire
    -0.15
    arias
    -0.15
    ammer
    -0.15
    edin
    -0.14
    NB
    -0.14
    POSITIVE LOGITS
    /out
    0.19
    Å¡ov
    0.16
    à¹Ģà¸ģ
    0.16
    olis
    0.15
    fty
    0.15
    ì²Ļ
    0.14
    æĺ
    0.14
    /AP
    0.14
     into
    0.14
    urons
    0.14
    Act Density 0.121%

    No Known Activations