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

    Neuronpedia

    INDEX
    Explanations

    instances of events happening, actions being taken, or developments occurring

    oai_token-act-pair · gpt-3.5-turbo

    instances of events and actions involving individuals in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.76
    quote
    -0.75
    endif
    -0.75
     Magicka
    -0.73
    Laughs
    -0.70
    ][/
    -0.70
    Anyway
    -0.69
     Lisp
    -0.68
     Anyway
    -0.67
    ntil
    -0.65
    POSITIVE LOGITS
     failed
    1.00
     botched
    0.91
     unsuccessful
    0.87
     unexpectedly
    0.85
     alleged
    0.79
     surfaced
    0.77
     accidentally
    0.77
     mistakenly
    0.75
     suspected
    0.75
     mysteriously
    0.75
    Act Density 0.354%

    No Known Activations