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

    Neuronpedia

    INDEX
    Explanations

    references to complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃo
    -0.14
    iore
    -0.14
    FLT
    -0.14
    æĽ
    -0.14
    avou
    -0.14
    187
    -0.14
    ound
    -0.14
     íĸ
    -0.13
    ublik
    -0.13
    ãĤ
    -0.13
    POSITIVE LOGITS
     frozen
    0.16
    321
    0.16
     rob
    0.15
    rozen
    0.15
    stk
    0.15
     PIC
    0.14
     Frozen
    0.14
     safe
    0.14
    0.14
    aga
    0.14
    Act Density 0.006%

    No Known Activations