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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or taking action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "go" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullah
    -0.76
    eer
    -0.74
    case
    -0.62
    ingham
    -0.62
    accompanied
    -0.61
    ÑĮ
    -0.60
    weather
    -0.60
    rance
    -0.59
    eve
    -0.57
    essa
    -0.57
    POSITIVE LOGITS
     overboard
    1.11
     toe
    0.86
    ggle
    0.83
    lems
    0.81
    verning
    0.80
    aded
    0.79
     furthe
    0.77
    ©¶æ
    0.72
     proactive
    0.72
     ahead
    0.71
    Act Density 0.138%

    No Known Activations