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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific professions or areas of work

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or patterns involving "the work of" followed by a reference to various professions or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.73
    orthy
    -0.72
    Edge
    -0.69
    edge
    -0.68
    ority
    -0.66
    irens
    -0.63
     Ples
    -0.63
    perture
    -0.63
    asta
    -0.62
    blast
    -0.60
    POSITIVE LOGITS
     Nanto
    0.81
     course
    0.72
     yours
    0.61
    itude
    0.61
     sorts
    0.60
    emouth
    0.58
    Kind
    0.58
    course
    0.58
     john
    0.58
     hindsight
    0.57
    Act Density 0.151%

    No Known Activations