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

    Neuronpedia

    INDEX
    Explanations

    references to the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egis
    -0.15
    arena
    -0.15
    cken
    -0.14
    sson
    -0.14
    ceph
    -0.14
    hof
    -0.14
    nock
    -0.13
    zag
    -0.13
    onta
    -0.13
    太éĥİ
    -0.13
    POSITIVE LOGITS
    ê°IJ
    0.15
    addon
    0.14
    ÅŁa
    0.14
    jÃŃm
    0.14
    480
    0.13
    oping
    0.13
    auce
    0.13
    erv
    0.13
    redicate
    0.13
    soever
    0.13
    Act Density 0.020%

    No Known Activations