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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TAMADRA
    -0.79
     grounding
    -0.77
     [|
    -0.76
     accent
    -0.73
     overtime
    -0.71
     Strikes
    -0.71
     Frenchman
    -0.70
     Parish
    -0.69
     Chair
    -0.69
     proposition
    -0.68
    POSITIVE LOGITS
    google
    1.76
    wikipedia
    1.52
    debian
    1.51
    yahoo
    1.49
    github
    1.47
    amazon
    1.44
    adobe
    1.44
    example
    1.41
    blogspot
    1.39
    wordpress
    1.38
    Act Density 0.063%

    No Known Activations