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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voting and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Architects
    -0.60
     sorely
    -0.60
     Helsinki
    -0.59
    ©¶æ
    -0.58
     chirop
    -0.57
     crocod
    -0.57
     Bosnia
    -0.57
     keyboards
    -0.56
     embassies
    -0.54
     Portug
    -0.54
    POSITIVE LOGITS
     versa
    0.87
    SPONSORED
    0.79
    .?
    0.79
    iltr
    0.76
     thereof
    0.75
    cellaneous
    0.75
    uple
    0.75
    ilde
    0.75
    oice
    0.75
    lite
    0.72
    Act Density 0.638%

    No Known Activations