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

    Neuronpedia

    INDEX
    Explanations

    key terms related to cybersecurity threats and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation, parentheses, or quotes

    np_acts-logits-general · gemini-2.0-flash

    reporting on achievements or claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.93
     myſelf
    -0.93
    ."</
    -0.86
     '\\;'
    -0.86
     auffi
    -0.81
     perſon
    -0.80
     purpoſe
    -0.78
    ".
    -0.78
    ſelves
    -0.77
     perfons
    -0.77
    POSITIVE LOGITS
     pretty
    1.07
     thingy
    1.06
     stuff
    0.99
     (!)
    0.97
     whatnot
    0.97
     apparently
    0.96
     weirdly
    0.95
     Apparently
    0.95
     folks
    0.95
     weird
    0.93
    Act Density 0.544%

    No Known Activations