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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments or praise

    oai_token-act-pair · gpt-3.5-turbo

    expressions of high praise or positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.98
    eter
    -0.77
    cling
    -0.74
    ilus
    -0.73
    bus
    -0.72
    SPONSORED
    -0.71
    former
    -0.69
    eters
    -0.69
    idon
    -0.66
    ©¶æ
    -0.65
    POSITIVE LOGITS
    sword
    0.89
     strides
    0.89
     introductory
    0.79
     opportunity
    0.78
    ãĥ¤
    0.73
     offence
    0.73
     enough
    0.72
     accomplishment
    0.71
     deal
    0.71
     teamwork
    0.71
    Act Density 0.034%

    No Known Activations