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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions given in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    instructions or steps presented in a list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ±
    -0.74
    ¶æ
    -0.71
    Publisher
    -0.69
    ©¶æ¥µ
    -0.67
    ¨
    -0.65
    oft
    -0.65
    ¥µ
    -0.64
    cedented
    -0.64
    Ń
    -0.64
    Ħ¢
    -0.63
    POSITIVE LOGITS
    :-
    1.17
    :(
    1.06
    :[
    1.05
    :
    1.02
    :"
    0.97
     viz
    0.86
    >:
    0.85
    %:
    0.80
    *:
    0.79
     :
    0.78
    Act Density 0.159%

    No Known Activations