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

    Neuronpedia

    INDEX
    Explanations

    shapes and geometric descriptors, especially those related to squares and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quake
    -0.17
    太éĥİ
    -0.17
    lessly
    -0.16
    å¦
    -0.15
    iw
    -0.14
     Merry
    -0.14
    ings
    -0.14
    udit
    -0.14
    eway
    -0.14
    bie
    -0.14
    POSITIVE LOGITS
    -shaped
    0.18
    angelo
    0.17
    asename
    0.16
    óż
    0.16
    /qu
    0.16
    à¥ĩत
    0.15
    íĺ
    0.15
    567
    0.15
    erb
    0.15
    /oct
    0.15
    Act Density 0.049%

    No Known Activations