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

    Neuronpedia

    INDEX
    Explanations

    terms related to density and denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ‘
    -1.07
     “
    -1.05
    ’
    -1.00
    =’
    -0.97
    .’
    -0.87
    ”
    -0.85
    ’.
    -0.84
    …’
    -0.83
    …”
    -0.83
    ”…
    -0.82
    POSITIVE LOGITS
    。"
    0.85
    brainly
    0.83
    StoryboardSegue
    0.82
     -"
    0.78
    ,'"
    0.77
    "¿
    0.76
    ："
    0.75
     estekak
    0.74
    ',"
    0.74
     "...
    0.72
    Act Density 0.119%

    No Known Activations