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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user interface design features

    oai_token-act-pair · gpt-3.5-turbo

    references to dropdown functionality in apps or menus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urally
    -0.73
    gregation
    -0.70
    eur
    -0.62
     caut
    -0.60
    aldo
    -0.60
    eering
    -0.59
     Franco
    -0.59
     Frey
    -0.58
    Prev
    -0.57
     Princ
    -0.57
    POSITIVE LOGITS
    kick
    1.14
    down
    1.12
    downs
    1.02
    outs
    0.96
    bear
    0.92
    zone
    0.83
    backs
    0.82
    DOWN
    0.81
     hints
    0.79
    offs
    0.79
    Act Density 0.027%

    No Known Activations