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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or analogies using the word "with"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oice
    -0.71
     respectively
    -0.69
    tackle
    -0.63
    idel
    -0.63
    Ingredients
    -0.63
     guiActiveUnfocused
    -0.63
    fw
    -0.62
    river
    -0.62
     DEFENSE
    -0.62
    istries
    -0.61
    POSITIVE LOGITS
     many
    1.21
     any
    1.09
     other
    1.06
     countless
    1.05
    lihood
    1.02
     most
    1.01
     others
    0.99
     previous
    0.95
     virtually
    0.89
     every
    0.88
    Act Density 0.218%

    No Known Activations