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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of a new era or significant change

    oai_token-act-pair · gpt-3.5-turbo

    references to various epochs or significant periods in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.65
    irrel
    -0.58
    weak
    -0.57
    versely
    -0.56
    oni
    -0.55
    ergus
    -0.55
     Rico
    -0.55
     condem
    -0.55
     Bakr
    -0.52
    morning
    -0.52
    POSITIVE LOGITS
     of
    1.06
    of
    0.85
     Of
    0.83
     OF
    0.81
     wherein
    0.77
     pioneered
    0.76
    Of
    0.76
     whereby
    0.75
    OF
    0.73
     where
    0.71
    Act Density 0.279%

    No Known Activations