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

    Neuronpedia

    INDEX
    Explanations

    modal verbs, particularly "can," indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aversable
    -0.15
    orsi
    -0.15
    acus
    -0.15
    optera
    -0.15
    793
    -0.15
    üst
    -0.14
    xfff
    -0.14
    ardown
    -0.14
    åģ
    -0.14
    erm
    -0.14
    POSITIVE LOGITS
    arded
    0.17
    sole
    0.15
     Howe
    0.15
    2
    0.15
     drives
    0.15
    abra
    0.15
    otope
    0.14
    Clo
    0.14
    not
    0.14
     missing
    0.14
    Act Density 0.112%

    No Known Activations