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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance and relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to important topics or issues in a context that emphasizes their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     admitting
    -0.71
     conced
    -0.62
     acquies
    -0.62
     retreating
    -0.61
     chalk
    -0.59
     Galile
    -0.58
     parting
    -0.58
    selves
    -0.57
     Gentleman
    -0.57
     Geo
    -0.57
    POSITIVE LOGITS
     mattered
    0.81
    oras
    0.71
    bleacher
    0.71
    irtual
    0.70
     matter
    0.68
    ora
    0.68
    matter
    0.66
    isode
    0.66
    APD
    0.63
     earthqu
    0.62
    Act Density 0.049%

    No Known Activations