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

    Neuronpedia

    INDEX
    Explanations

    financial amounts expressed in a special format

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols used in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crusher
    -0.75
    enegger
    -0.72
    doms
    -0.69
    EngineDebug
    -0.66
     gad
    -0.66
    itar
    -0.65
     Tid
    -0.65
    Downloadha
    -0.65
     Pension
    -0.64
    sonian
    -0.64
    POSITIVE LOGITS
    Ħ¢
    1.47
    Ĥ
    1.45
    Ħ
    1.45
    Ĥª
    1.40
    ĵ
    1.37
    Į
    1.37
    ł
    1.36
    ħ
    1.32
    Ĭ
    1.31
    ĥ
    1.30
    Act Density 0.017%

    No Known Activations