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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions or taking actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "you have" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ®
    -0.75
    oshi
    -0.73
    cus
    -0.72
     Indeed
    -0.68
    WH
    -0.66
    soon
    -0.66
     Soon
    -0.65
    AFP
    -0.65
     Else
    -0.64
    ãĤ´
    -0.63
    POSITIVE LOGITS
     somebody
    1.08
     lots
    1.07
     gotta
    1.00
     tremendous
    1.00
     loads
    0.91
     tons
    0.90
     guys
    0.89
     everybody
    0.89
     gonna
    0.88
     tonnes
    0.87
    Act Density 0.244%

    No Known Activations