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

    Neuronpedia

    INDEX
    Explanations

    information about personal anecdotes or accounts involving interaction and experience

    oai_token-act-pair · gpt-3.5-turbo

    mentions of storytelling or accounts of personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gate
    -0.71
    available
    -0.69
    clock
    -0.69
    icons
    -0.69
    Copy
    -0.68
    hold
    -0.68
    worthiness
    -0.68
    wei
    -0.67
    printf
    -0.66
    hm
    -0.66
    POSITIVE LOGITS
     experiences
    1.09
     harrowing
    1.06
     adventures
    1.00
     overcoming
    0.99
     hardships
    0.98
     encountering
    0.98
     struggles
    0.95
     frustrations
    0.95
     encounters
    0.93
     experience
    0.91
    Act Density 0.304%

    No Known Activations