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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with the act of doing or performing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urnal
    -0.71
    imentary
    -0.71
    >[
    -0.68
     peculiar
    -0.67
     veins
    -0.64
     wounding
    -0.63
    izarre
    -0.62
     barring
    -0.61
     unexpl
    -0.60
     magically
    -0.60
    POSITIVE LOGITS
     Yourself
    1.03
     Loud
    0.83
     Away
    0.80
     Slowly
    0.78
     Grow
    0.78
     Damn
    0.76
    !,
    0.75
     Later
    0.74
     Matters
    0.74
    Daddy
    0.74
    Act Density 0.266%

    No Known Activations