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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assistance and guidance, particularly in helping and informing users

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people or users in contexts related to products and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.73
    ASED
    -0.67
    ascar
    -0.60
    tein
    -0.52
    ced
    -0.52
    ITED
    -0.52
     Trilogy
    -0.51
    TPS
    -0.51
    NING
    -0.51
     Alloy
    -0.50
    POSITIVE LOGITS
    folk
    0.67
     understand
    0.65
     beware
    0.64
    mbuds
    0.64
    opausal
    0.63
     recognize
    0.62
     interested
    0.62
     adopt
    0.61
    perty
    0.61
     congreg
    0.61
    Act Density 0.422%

    No Known Activations