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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "default" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gwia
    -0.51
     meat
    -0.48
     onAnimation
    -0.47
     Juda
    -0.47
    setLast
    -0.47
     feminina
    -0.46
     Meat
    -0.45
    (`/
    -0.45
    LUT
    -0.44
     vocês
    -0.44
    POSITIVE LOGITS
     default
    1.33
    __':
    1.13
    __':
    1.13
    Datuak
    1.09
    __":
    1.07
     defaults
    1.06
    __":
    1.01
    default
    0.98
     Defaults
    0.95
    //
    0.94
    Act Density 0.014%

    No Known Activations