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

    Neuronpedia

    INDEX
    Explanations

    technical terms and measurements related to mechanisms and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     piú
    -0.71
     […]
    -0.67
     étoient
    -0.64
    &#
    -0.62
     étoit
    -0.59
    &
    -0.59
    PasswordEncoder
    -0.56
     BrowserModule
    -0.55
    […]
    -0.54
     به‌
    -0.53
    POSITIVE LOGITS
    0.68
    Again
    0.67
    ">+
    0.66
    "]];
    0.65
     Again
    0.65
    ̈́
    0.65
    ><><
    0.64
     again
    0.63
    niająca
    0.58
     noDo
    0.57
    Act Density 0.026%

    No Known Activations