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

    Neuronpedia

    INDEX
    Explanations

    words related to being impressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions and variations of the word "impressed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angled
    -0.66
    nown
    -0.65
    quarters
    -0.65
    loe
    -0.62
    sun
    -0.61
     ��������
    -0.61
     landfill
    -0.61
    arians
    -0.60
     saline
    -0.60
    ouple
    -0.59
    POSITIVE LOGITS
    mented
    0.94
    ments
    0.89
    MENTS
    0.82
    ively
    0.82
     impressed
    0.82
    ment
    0.77
    ulously
    0.75
    MENT
    0.74
    mentation
    0.71
    iated
    0.71
    Act Density 0.022%

    No Known Activations