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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intention and actions

    oai_token-act-pair · gpt-3.5-turbo

    present tense verbs indicating a person's actions or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.76
    equality
    -0.74
     Customers
    -0.69
     Values
    -0.66
     antid
    -0.66
    isSpecialOrderable
    -0.64
    irmation
    -0.63
    TPS
    -0.62
    mate
    -0.62
     Lessons
    -0.61
    POSITIVE LOGITS
     himself
    0.98
     herself
    0.86
     calmly
    0.83
     whom
    0.74
     remorse
    0.73
     bluff
    0.73
    ère
    0.73
    gery
    0.72
     narr
    0.65
     maneu
    0.64
    Act Density 0.506%

    No Known Activations