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

    Neuronpedia

    INDEX
    Explanations

    the word "how" preceded by another word

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases and questions related to understanding or clarifying situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.86
     dime
    -0.82
     critical
    -0.74
     subjective
    -0.74
     subdiv
    -0.71
     hell
    -0.70
     chronically
    -0.69
     outl
    -0.69
     bureaucr
    -0.69
     altern
    -0.68
    POSITIVE LOGITS
    inite
    0.93
    ption
    0.93
    ius
    0.87
    enges
    0.85
    olean
    0.84
    atis
    0.84
    hess
    0.83
    stad
    0.83
    enh
    0.81
    enment
    0.79
    Act Density 0.369%

    No Known Activations