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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    635
    -0.17
    ãĥ¼ãĥĦ
    -0.15
    si
    -0.14
    Č
    -0.14
    okus
    -0.14
    vert
    -0.14
    ÙĦÙħاÙĨ
    -0.14
     бой
    -0.14
     rast
    -0.14
    λιά
    -0.13
    POSITIVE LOGITS
     com
    0.27
     org
    0.21
    IRO
    0.17
    org
    0.17
     edu
    0.16
    reta
    0.16
     Virgin
    0.14
     ;
    0.14
     Org
    0.14
    usher
    0.14
    Act Density 0.008%

    No Known Activations