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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance, taking action, and projects

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing the importance of various actions or concepts in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mage
    -0.64
     Mage
    -0.64
     Levant
    -0.60
    å°Ĩ
    -0.59
    ilings
    -0.58
     crow
    -0.58
    shaw
    -0.57
    geries
    -0.57
    bow
    -0.56
     Ferguson
    -0.55
    POSITIVE LOGITS
    imaru
    0.70
     impossible
    0.67
     easiest
    0.66
     aggrav
    0.65
    ibaba
    0.64
    kaya
    0.63
    ioned
    0.62
     easier
    0.62
     unclear
    0.62
     ironic
    0.61
    Act Density 1.312%

    No Known Activations