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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the action of putting someone or something in a certain position or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an action that imposes pressure or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.75
     Examiner
    -0.65
    issance
    -0.63
     Conquer
    -0.61
     Sample
    -0.60
     Scrolls
    -0.57
    uary
    -0.56
     Loving
    -0.55
     Observer
    -0.55
    CHAT
    -0.55
    POSITIVE LOGITS
     pressure
    0.96
     undue
    0.89
    arnaev
    0.88
     downward
    0.84
    eki
    0.83
     aside
    0.83
     forth
    0.83
     strain
    0.82
    tering
    0.80
     toget
    0.79
    Act Density 0.049%

    No Known Activations