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

    Neuronpedia

    INDEX
    Explanations

    specifically the word "your"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "your" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.95
    forth
    -0.82
     Goes
    -0.74
     Cohn
    -0.74
     Originally
    -0.71
    ilts
    -0.71
    Hour
    -0.69
    ween
    -0.68
    Æ
    -0.68
    wik
    -0.68
    POSITIVE LOGITS
     own
    1.36
     favourite
    1.19
     favorite
    1.08
    selves
    0.94
    anmar
    0.92
     adversary
    0.89
     opponent
    0.87
    ocard
    0.85
     subscription
    0.85
    self
    0.85
    Act Density 0.105%

    No Known Activations