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

    Neuronpedia

    INDEX
    Explanations

    terminology related to goal-setting or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express objectives or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sapp
    -0.75
    flush
    -0.74
     Beet
    -0.72
    Lot
    -0.69
    due
    -0.64
    late
    -0.62
     Marino
    -0.61
    Abyss
    -0.60
    uddin
    -0.60
    Sax
    -0.60
    POSITIVE LOGITS
     goal
    0.78
     thrust
    0.74
    Goal
    0.72
    lessly
    0.70
     motiv
    0.69
    ultimate
    0.68
    atform
    0.68
     limitation
    0.68
     audience
    0.67
     motive
    0.66
    Act Density 0.125%

    No Known Activations