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

    Neuronpedia

    INDEX
    Explanations

    prepositions and verbs indicating a connection or action with strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases that indicate relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terness
    -0.58
    grain
    -0.54
    Champ
    -0.53
    anners
    -0.52
    spec
    -0.51
    ians
    -0.51
    olicy
    -0.51
    gged
    -0.50
    arty
    -0.50
    chanted
    -0.50
    POSITIVE LOGITS
     anyways
    0.89
     besides
    0.85
     nowadays
    0.83
     lately
    0.81
    .
    0.81
     during
    0.81
     anyway
    0.80
     beforehand
    0.79
    .:
    0.79
    .,
    0.77
    Act Density 0.176%

    No Known Activations