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

    Neuronpedia

    INDEX
    Explanations

    terms related to participation and participation-related language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halt
    -0.17
    tle
    -0.16
    isé
    -0.15
    332
    -0.15
    ailability
    -0.15
    hind
    -0.15
     Malone
    -0.15
    ät
    -0.15
    warts
    -0.15
    INGER
    -0.14
    POSITIVE LOGITS
    atory
    0.21
    cip
    0.17
     particip
    0.16
    çħ§
    0.16
    abra
    0.15
    PLE
    0.15
    æk
    0.15
    pla
    0.15
    ipation
    0.15
    iple
    0.15
    Act Density 0.009%

    No Known Activations