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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions or having options

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making choices or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uum
    -0.84
    brance
    -0.77
    velop
    -0.74
    steen
    -0.73
    vae
    -0.73
    older
    -0.72
    zona
    -0.71
    peria
    -0.71
    awar
    -0.71
    estone
    -0.70
    POSITIVE LOGITS
     choices
    1.12
     choice
    1.00
    axe
    0.83
     options
    0.81
    Choice
    0.80
     chose
    0.79
    choice
    0.79
     Altern
    0.78
     Choice
    0.78
    é¾įå¥ij士
    0.77
    Act Density 0.037%

    No Known Activations