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

    Neuronpedia

    INDEX
    Explanations

    links or commands related to opening new windows or popup windows

    oai_token-act-pair · gpt-3.5-turbo

    references to browser windows or pop-ups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haram
    -0.81
    IGH
    -0.81
    ghan
    -0.78
    icit
    -0.76
    avez
    -0.71
    avid
    -0.70
    agonist
    -0.67
    ector
    -0.66
    uca
    -0.66
    icient
    -0.64
    POSITIVE LOGITS
     pane
    0.92
    glass
    0.91
     sill
    0.87
     window
    0.84
     windows
    0.83
    window
    0.80
     Window
    0.79
    eering
    0.79
    edin
    0.75
    caps
    0.74
    Act Density 0.012%

    No Known Activations