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

    Neuronpedia

    INDEX
    Explanations

    actions related to carrying out a specific objective

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or conditions that follow a specified order or protocol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tex
    -0.71
    irted
    -0.67
    ider
    -0.66
    redited
    -0.64
    nis
    -0.60
    ritten
    -0.60
    milo
    -0.60
    ky
    -0.60
    etheless
    -0.59
    tek
    -0.59
    POSITIVE LOGITS
     Osw
    0.90
    lies
    0.69
    ppel
    0.69
     bolster
    0.67
     fulfillment
    0.66
     fres
    0.65
    meal
    0.64
     ensure
    0.64
    liness
    0.63
     alleviate
    0.63
    Act Density 0.017%

    No Known Activations