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

    Neuronpedia

    INDEX
    Explanations

    words related to accolades, recognition, and distinction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "honor" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ange
    -0.78
    hover
    -0.76
    arre
    -0.74
    Done
    -0.72
     Aber
    -0.70
    ppo
    -0.66
     fielded
    -0.63
    TPPStreamerBot
    -0.63
    Mos
    -0.61
    WER
    -0.61
    POSITIVE LOGITS
     honors
    1.18
    ably
    1.13
    abilia
    1.08
     honored
    1.03
     honoured
    1.03
     honor
    0.96
     honour
    0.91
    itism
    0.91
     honoring
    0.88
    uous
    0.83
    Act Density 0.014%

    No Known Activations