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

    Neuronpedia

    INDEX
    Explanations

    structures and arrangements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consist
    -0.16
    eldom
    -0.16
    chet
    -0.14
    ondo
    -0.14
    iph
    -0.14
    ìĦŃ
    -0.14
    åħ¼
    -0.14
    igital
    -0.14
    _lists
    -0.14
    cco
    -0.13
    POSITIVE LOGITS
     arranged
    0.29
     around
    0.28
     arrangement
    0.26
     autour
    0.25
     surrounding
    0.24
    around
    0.24
     forming
    0.23
     вокÑĢÑĥг
    0.23
     array
    0.23
     circle
    0.23
    Act Density 0.295%

    No Known Activations