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

    Neuronpedia

    INDEX
    Explanations

    phrases related to falling

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iola
    -0.70
    folios
    -0.65
    archives
    -0.62
    iliary
    -0.62
    andan
    -0.61
    eering
    -0.60
    eur
    -0.60
    heid
    -0.59
    ansas
    -0.59
    cius
    -0.58
    POSITIVE LOGITS
     asleep
    1.00
    opian
    0.94
    graded
    0.83
    acies
    0.83
     jaws
    0.82
    hill
    0.80
    down
    0.79
    stairs
    0.76
    gradient
    0.75
     overboard
    0.74
    Act Density 4.403%

    No Known Activations