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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to upward movement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.21
    esters
    -0.17
    odore
    -0.15
    tempt
    -0.15
    zÅij
    -0.15
    .uk
    -0.15
    س
    -0.15
    cury
    -0.15
    lum
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    POSITIVE LOGITS
    /down
    0.25
    datable
    0.24
    sk
    0.18
    shot
    0.17
    sert
    0.17
    turned
    0.17
    dater
    0.17
    draft
    0.16
    ture
    0.16
    ski
    0.15
    Act Density 0.195%

    No Known Activations