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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to various processes and actions in the context of scientific and technical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    之
    -0.59
     expanded
    -0.59
    cination
    -0.58
    ation
    -0.58
    _
    -0.57
    ity
    -0.56
    ization
    -0.56
    ction
    -0.54
    mation
    -0.54
    gence
    -0.54
    POSITIVE LOGITS
    AsUp
    0.87
     piú
    0.87
    __':
    0.86
     myſelf
    0.80
     electing
    0.80
    cydow
    0.79
     ogrod
    0.79
    __":
    0.78
    VELOP
    0.78
    "]),
    0.77
    Act Density 1.115%

    No Known Activations