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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "including."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flen
    -0.17
    inand
    -0.15
     Cous
    -0.15
    RR
    -0.15
    yal
    -0.15
    ison
    -0.14
    jsonp
    -0.14
    modifiable
    -0.13
     messenger
    -0.13
    Transpose
    -0.13
    POSITIVE LOGITS
    ecta
    0.15
    CLUD
    0.15
    utdown
    0.15
    маз
    0.15
    شة
    0.14
    amilia
    0.14
    ares
    0.14
    kke
    0.14
     kia
    0.14
    udur
    0.13
    Act Density 0.080%

    No Known Activations