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

    Neuronpedia

    INDEX
    Explanations

    phrases related to upward movement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    t
    -0.22
    esters
    -0.19
    tube
    -0.18
    est
    -0.17
    ectomy
    -0.17
    odore
    -0.17
    IAL
    -0.17
    ect
    -0.16
    esting
    -0.16
    quin
    -0.15
    POSITIVE LOGITS
    /down
    0.38
    datable
    0.33
    pers
    0.28
    gradable
    0.26
    ped
    0.26
    dater
    0.25
    ping
    0.25
    sert
    0.23
    turned
    0.23
    graded
    0.22
    Act Density 0.177%

    No Known Activations