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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "you" is followed by a directional mark in ASCII art

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol that appears frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickets
    -0.81
    undown
    -0.74
     Palestin
    -0.68
     Instr
    -0.67
     telesc
    -0.66
     adolesc
    -0.65
     paperback
    -0.65
    ModLoader
    -0.62
     fortun
    -0.62
     CLR
    -0.62
    POSITIVE LOGITS
    own
    0.88
    swer
    0.85
    else
    0.83
    agree
    0.83
    ï¸ı
    0.81
    ski
    0.79
    sure
    0.77
    audi
    0.76
    tre
    0.76
    lean
    0.75
    Act Density 0.107%

    No Known Activations