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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up or registering for something

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases about signing up for services or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     delic
    -0.70
    BIT
    -0.69
     portrayed
    -0.66
     bis
    -0.65
     Gim
    -0.60
     pie
    -0.60
     utmost
    -0.60
    phy
    -0.59
     dispro
    -0.59
     depiction
    -0.58
    POSITIVE LOGITS
    skirts
    0.93
    adesh
    0.85
    lish
    0.82
    river
    0.81
    ateful
    0.79
    à¼
    0.77
    ancies
    0.75
    rights
    0.75
    swing
    0.75
    ername
    0.75
    Act Density 0.021%

    No Known Activations