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

    Neuronpedia

    INDEX
    Explanations

    links or calls to action in the context of sharing or distributing a story

    oai_token-act-pair · gpt-3.5-turbo

    actions related to sharing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.86
    anwhile
    -0.84
     desper
    -0.79
    schild
    -0.78
     destro
    -0.76
    etheless
    -0.76
     submar
    -0.74
    untarily
    -0.72
    icably
    -0.71
     annexed
    -0.71
    POSITIVE LOGITS
    holder
    1.14
    holders
    1.04
    ership
    0.93
    cro
    0.93
     Share
    0.92
    holding
    0.78
    ables
    0.77
    hare
    0.76
    Tweet
    0.75
    Point
    0.75
    Act Density 0.018%

    No Known Activations