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

    Neuronpedia

    INDEX
    Explanations

    pronouns 'them', focused on when they are preceded by a specific number in numerical context

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "them" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RTX
    -0.82
    mire
    -0.71
    Limit
    -0.63
    Pause
    -0.62
     Union
    -0.61
    politics
    -0.60
     Farn
    -0.59
    =-=-
    -0.59
    gg
    -0.59
    00000
    -0.58
    POSITIVE LOGITS
    atic
    0.98
    alian
    0.86
    atically
    0.84
     succeeded
    0.83
     perished
    0.78
     survives
    0.78
     involved
    0.74
     originated
    0.74
     lasted
    0.72
     selves
    0.72
    Act Density 0.040%

    No Known Activations