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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating choice or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ̣
    -0.17
    ayo
    -0.17
    uco
    -0.17
    ople
    -0.17
    hammer
    -0.16
    bpp
    -0.15
    ware
    -0.15
    plied
    -0.14
    olec
    -0.14
    intColor
    -0.14
    POSITIVE LOGITS
    ìĩ¼
    0.16
    IOD
    0.15
     conjug
    0.14
    elts
    0.14
    antz
    0.14
    кÑĢа
    0.14
     Record
    0.14
     recipro
    0.13
     Klein
    0.13
    jug
    0.13
    Act Density 0.010%

    No Known Activations