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

    Neuronpedia

    INDEX
    Explanations

    comparative words indicating an increase or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize an increasing quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.76
    OCK
    -0.75
    ����
    -0.72
    xtap
    -0.72
    borg
    -0.71
    IENCE
    -0.67
     Accounting
    -0.66
    selves
    -0.66
    ��
    -0.64
     Classification
    -0.64
    POSITIVE LOGITS
     than
    0.90
     complicated
    0.87
     expensive
    0.86
     adventurous
    0.84
     frequent
    0.83
    ls
    0.81
     manageable
    0.81
     affluent
    0.80
     elaborate
    0.80
     generous
    0.80
    Act Density 0.035%

    No Known Activations