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

    Neuronpedia

    INDEX
    Explanations

    patterns and relationships involving numbers and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÇIJ
    -0.16
     Ost
    -0.15
    ost
    -0.15
     oct
    -0.15
     Oct
    -0.14
    swick
    -0.14
    ãĥĭãĤ¢
    -0.14
    ÐĬ
    -0.14
    æĺŃ
    -0.14
    ifes
    -0.14
    POSITIVE LOGITS
    12
    0.94
     twelve
    0.77
     Twelve
    0.75
    åįģäºĮ
    0.71
     XII
    0.60
    Û±Û²
    0.58
    012
    0.50
     dozen
    0.43
    Tw
    0.43
     tw
    0.38
    Act Density 0.045%

    No Known Activations