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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and structures like functions, variables, and classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exitRule
    -0.67
     للمعارف
    -0.65
    endpush
    -0.62
     queſta
    -0.54
     estekak
    -0.53
     autorytatywna
    -0.51
    PyExc
    -0.49
     ſind
    -0.49
    ########.
    -0.48
     ſche
    -0.48
    POSITIVE LOGITS
    hyrchwyd
    0.49
     ويكيپيديا
    0.47
    AnchorStyles
    0.46
     Wicidata
    0.42
    abestanden
    0.37
     sogen
    0.36
    曖昧さ回避
    0.36
    渡
    0.35
     FUCKING
    0.35
     poked
    0.35
    Act Density 0.854%

    No Known Activations