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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "largely" occurs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prevailing trends or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anth
    -0.75
     Chaser
    -0.72
    abad
    -0.69
    atures
    -0.68
    yle
    -0.68
     Kard
    -0.66
    endi
    -0.66
     Ambassador
    -0.66
     Probe
    -0.65
    yers
    -0.65
    POSITIVE LOGITS
     unchanged
    0.94
     reliant
    0.91
     overlooked
    0.90
     unaffected
    0.89
     consist
    0.86
     comprised
    0.86
     consisted
    0.85
     absent
    0.84
     lacking
    0.83
     relying
    0.83
    Act Density 0.022%

    No Known Activations