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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that focus on uncertainty or making choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.76
    kamp
    -0.72
    emp
    -0.71
    isol
    -0.71
    limited
    -0.71
    shi
    -0.70
    istically
    -0.69
    ivism
    -0.69
    ISTORY
    -0.69
    mur
    -0.68
    POSITIVE LOGITS
     kinds
    1.04
     ones
    1.01
     wavelengths
    0.99
     direction
    0.93
     side
    0.92
     parts
    0.89
     types
    0.88
     aspects
    0.88
     sorts
    0.84
     hemisphere
    0.83
    Act Density 0.056%

    No Known Activations