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

    Neuronpedia

    INDEX
    Explanations

    words related to ongoing or continuous actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words indicating ongoing actions or persistent situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eah
    -0.79
    ère
    -0.74
    idden
    -0.72
    ique
    -0.70
    sters
    -0.70
    iman
    -0.69
    inators
    -0.67
    ifty
    -0.66
    ousse
    -0.65
    ustomed
    -0.64
    POSITIVE LOGITS
     developments
    0.77
     hostilities
    0.73
     viability
    0.71
     engagements
    0.71
     strugg
    0.71
     sclerosis
    0.70
     appropriations
    0.69
    ance
    0.69
    uum
    0.69
     vitality
    0.67
    Act Density 0.016%

    No Known Activations