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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clicking actions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to user interaction with links or buttons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nia
    -0.67
     Scotia
    -0.66
     Scand
    -0.61
    qqa
    -0.61
     Janeiro
    -0.60
    nam
    -0.58
    ãĤ£
    -0.58
     Yuk
    -0.57
    venge
    -0.57
    otype
    -0.57
    POSITIVE LOGITS
    lish
    0.87
    wheel
    0.83
    views
    0.75
    river
    0.72
    lems
    0.70
    atson
    0.68
     isEnabled
    0.68
    jriwal
    0.67
    hops
    0.66
    bots
    0.66
    Act Density 0.010%

    No Known Activations