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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "getting on" or moving forward with an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     localization
    -0.62
     sparing
    -0.60
     Mandarin
    -0.59
     omission
    -0.56
     Methods
    -0.55
     cryptic
    -0.55
     locale
    -0.55
     Detected
    -0.54
     caution
    -0.53
    WARE
    -0.53
    POSITIVE LOGITS
    eline
    0.82
    udeb
    0.75
    soc
    0.73
    abit
    0.72
    andro
    0.70
    eworld
    0.69
    clerosis
    0.68
    itiveness
    0.67
     foothold
    0.65
    touch
    0.65
    Act Density 0.045%

    No Known Activations