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

    Neuronpedia

    INDEX
    Explanations

    phrases that express hesitation or caution in making claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ken
    -0.18
    ynam
    -0.15
    ê²ł
    -0.15
     Blackburn
    -0.15
    ahl
    -0.14
    ê°Ŀ
    -0.14
    acci
    -0.14
    kola
    -0.14
    woff
    -0.13
    ศร
    -0.13
    POSITIVE LOGITS
    oten
    0.15
     Cru
    0.15
    space
    0.15
    ilin
    0.14
    ìĦŃ
    0.14
    thrown
    0.14
    sd
    0.14
    CCA
    0.14
    allery
    0.14
    site
    0.14
    Act Density 0.385%

    No Known Activations