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

    Neuronpedia

    INDEX
    Explanations

    verbs and adjectives that describe disturbance or disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oster
    -0.18
    naissance
    -0.18
    vyk
    -0.17
    utton
    -0.16
    utow
    -0.15
    atto
    -0.15
    arie
    -0.15
     klu
    -0.14
    ICIENT
    -0.14
    464
    -0.14
    POSITIVE LOGITS
     state
    0.16
    лиÑĨ
    0.16
     tall
    0.16
     pale
    0.16
     pam
    0.15
    tml
    0.15
     Gro
    0.15
     ob
    0.15
    /raw
    0.15
    央
    0.15
    Act Density 0.197%

    No Known Activations