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

    Neuronpedia

    INDEX
    Explanations

    specific entities or organizations related to lists or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to lists and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     irregularities
    -0.67
     apprehend
    -0.64
    erest
    -0.62
    resso
    -0.62
     noises
    -0.61
    zees
    -0.61
    oa
    -0.60
     prostitutes
    -0.59
     earnest
    -0.59
     interrupts
    -0.59
    POSITIVE LOGITS
     list
    1.99
    list
    1.57
     lists
    1.54
     roster
    1.41
     repertoire
    1.39
     checklist
    1.38
     LIST
    1.38
     Lists
    1.37
     List
    1.37
    LIST
    1.36
    Act Density 0.964%

    No Known Activations