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

    Neuronpedia

    INDEX
    Explanations

    references to geographic directions and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhan
    -0.17
    ymous
    -0.16
    ucher
    -0.16
    inium
    -0.15
    ully
    -0.15
     numberWith
    -0.14
    ceae
    -0.14
    UCH
    -0.14
    apg
    -0.14
    pha
    -0.14
    POSITIVE LOGITS
     direction
    0.17
    emas
    0.15
     toward
    0.14
     à¤Ńर
    0.14
    ови
    0.14
     lá»ĩ
    0.13
    roup
    0.13
    ç¾½
    0.13
    ayah
    0.13
     Ø£ÙĪÙĦ
    0.13
    Act Density 0.074%

    No Known Activations