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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or characters that may represent distinct concepts or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     testament
    -0.15
    SGlobal
    -0.14
     transitioning
    -0.14
    ugin
    -0.13
     [...
    -0.13
    Ïģεί
    -0.13
    imedia
    -0.13
    å¦ĥ
    -0.13
     [...]
    -0.13
    LOSE
    -0.13
    POSITIVE LOGITS
     Tray
    0.21
    196
    0.16
     folk
    0.16
     tray
    0.16
     Cliff
    0.15
     Alf
    0.15
    anke
    0.15
     Len
    0.15
     Mick
    0.15
     trays
    0.15
    Act Density 0.004%

    No Known Activations