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

    Neuronpedia

    INDEX
    Explanations

    adjective phrases used to describe something or someone

    oai_token-act-pair · gpt-3.5-turbo

    descriptions or evaluations of various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.77
    utical
    -0.71
    Side
    -0.69
    bucks
    -0.67
    iership
    -0.65
    rone
    -0.63
    IELD
    -0.62
    OTAL
    -0.60
    RL
    -0.60
    EA
    -0.59
    POSITIVE LOGITS
     "âĢ¦
    1.00
     "...
    1.00
     follows
    0.98
     "
    0.89
     "'
    0.85
     having
    0.82
     "[
    0.82
     well
    0.80
    pires
    0.76
     being
    0.76
    Act Density 0.071%

    No Known Activations