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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating a desire or preference

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Xuan
    -0.63
     Trap
    -0.61
     Gutenberg
    -0.61
    Frag
    -0.59
     Fortune
    -0.59
     Kag
    -0.59
     Gad
    -0.59
     Kinder
    -0.59
    pires
    -0.58
     Hebdo
    -0.58
    POSITIVE LOGITS
     advise
    1.14
     recommend
    1.12
     sugg
    1.08
     gladly
    1.05
     prefer
    1.04
     characterize
    1.03
     appreciate
    1.00
     nominate
    1.00
     suggest
    0.99
     expect
    0.98
    Act Density 0.071%

    No Known Activations