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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating investigation or consideration of a topic

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "look into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ienne
    -0.65
    hop
    -0.63
     farewell
    -0.62
    bender
    -0.62
    warning
    -0.60
    owl
    -0.60
    END
    -0.59
    present
    -0.58
     acquitted
    -0.58
    NES
    -0.57
    POSITIVE LOGITS
    âĸijâĸij
    0.73
    zag
    0.69
     feasibility
    0.68
     whats
    0.66
     Coinbase
    0.65
    effic
    0.63
     whether
    0.62
    izons
    0.62
    agall
    0.62
     Divinity
    0.62
    Act Density 0.026%

    No Known Activations