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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing intensity or completion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of significance or emphasis in the context provided

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allery
    -0.71
    umbai
    -0.70
    glomer
    -0.70
    anwhile
    -0.67
    hower
    -0.65
    pherd
    -0.65
    ode
    -0.61
    here
    -0.61
    dinand
    -0.60
    ilight
    -0.60
    POSITIVE LOGITS
     impunity
    1.04
     regard
    0.96
     regards
    0.93
     intention
    0.91
     hindsight
    0.91
     abandon
    0.90
     ease
    0.88
     caveat
    0.83
     intent
    0.81
     caveats
    0.80
    Act Density 0.338%

    No Known Activations