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

    Neuronpedia

    INDEX
    Explanations

    buttons or tabs related to different actions or functionalities in a user interface

    oai_token-act-pair · gpt-3.5-turbo

    user interface elements and actions related to buttons and tabs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.78
    sbm
    -0.75
    yrics
    -0.73
    bred
    -0.68
    nesses
    -0.67
    stud
    -0.67
    isen
    -0.66
    hern
    -0.66
    gone
    -0.66
    姫
    -0.64
    POSITIVE LOGITS
     tracker
    0.76
     Tracker
    0.70
    unciation
    0.68
    naire
    0.68
     Badge
    0.67
     Toggle
    0.65
     bloc
    0.65
     Strip
    0.64
     itself
    0.63
     strip
    0.61
    Act Density 0.240%

    No Known Activations