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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict and confrontation

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to constructs and measurements in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chev
    -0.78
    \/\/
    -0.69
     labels
    -0.68
    agara
    -0.67
    itsch
    -0.64
     entitle
    -0.62
    ItemThumbnailImage
    -0.60
     composer
    -0.59
    idays
    -0.58
     invaders
    -0.57
    POSITIVE LOGITS
    ciating
    0.83
    nces
    0.82
    enment
    0.80
    rences
    0.77
    rency
    0.77
    liction
    0.75
    Sys
    0.75
    ctions
    0.74
    uration
    0.72
    ulative
    0.71
    Act Density 0.075%

    No Known Activations