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

    Neuronpedia

    INDEX
    Explanations

    present tense verbs describing actions or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sg
    -0.69
    lights
    -0.68
    isu
    -0.67
    opol
    -0.66
     Prosecutor
    -0.65
    ESA
    -0.63
     Secondly
    -0.63
    case
    -0.59
     Prosecutors
    -0.59
    Secondly
    -0.59
    POSITIVE LOGITS
     laundry
    0.92
     something
    0.88
    omsday
    0.87
    pez
    0.84
     nothing
    0.82
    omething
    0.81
     chores
    0.79
     homework
    0.79
    ggy
    0.78
     wonders
    0.75
    Act Density 0.121%

    No Known Activations