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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various types of information and content such as staff information, video information, album information, and technical upgrades

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of informational content, events, or organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osi
    -0.94
    à¨
    -0.76
    umo
    -0.75
    inous
    -0.73
    forcement
    -0.68
    gage
    -0.68
    ynt
    -0.68
    assian
    -0.68
    imil
    -0.65
    opping
    -0.65
    POSITIVE LOGITS
     blah
    0.59
     explorer
    0.58
     socialism
    0.57
     director
    0.57
     mornings
    0.56
     alert
    0.56
     morning
    0.56
     located
    0.56
     roundup
    0.56
     autism
    0.55
    Act Density 0.608%

    No Known Activations