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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "may" or its variations are used to indicate possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istra
    -0.16
    aterno
    -0.15
    isoft
    -0.14
    ailer
    -0.14
    ÃĹ↵↵
    -0.14
    inia
    -0.14
    (___
    -0.14
    isas
    -0.14
    aylight
    -0.14
    istrovstvÃŃ
    -0.14
    POSITIVE LOGITS
     be
    0.32
    hem
    0.25
    onna
    0.23
    ors
    0.22
    ily
    0.21
    oral
    0.21
    ORS
    0.18
    hap
    0.18
    -have
    0.18
     not
    0.18
    Act Density 0.107%

    No Known Activations