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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the importance of specific situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    explanations and justifications in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apsed
    -0.72
    inis
    -0.68
    lez
    -0.67
    fml
    -0.65
     scr
    -0.65
    inse
    -0.64
    floor
    -0.61
    ascus
    -0.60
    inate
    -0.59
     tyr
    -0.59
    POSITIVE LOGITS
    */(
    0.73
     Firstly
    0.72
    ecause
    0.71
     ][
    0.71
     unlike
    0.69
     suppose
    0.68
     although
    0.68
     evidenced
    0.65
     "[
    0.64
     neither
    0.63
    Act Density 0.241%

    No Known Activations