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

    Neuronpedia

    INDEX
    Explanations

    statements or facts that end with punctuation marks like periods or commas

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate a significant event or statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brill
    -0.78
     honoured
    -0.75
     welcome
    -0.74
     favourite
    -0.72
     organise
    -0.71
     endeavour
    -0.71
     elbow
    -0.70
    isable
    -0.70
     handshake
    -0.69
     rubbish
    -0.68
    POSITIVE LOGITS
    âĢ
    1.99
    »
    1.41
    âĹı
    1.40
     âĢ
    1.39
    ãĢ
    1.38
    âĢł
    1.35
    1.35
    **
    1.33
    âĻ¦
    1.26
    âĸł
    1.26
    Act Density 0.612%

    No Known Activations