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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing obligation and conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     has
    -0.47
     Has
    -0.43
    has
    -0.41
    Has
    -0.39
     seems
    -0.39
    retudo
    -0.35
    Seems
    -0.33
     scheint
    -0.30
     lately
    -0.30
     parecía
    -0.30
    POSITIVE LOGITS
     have
    0.88
     haber
    0.78
    ьаж
    0.73
    GTCX
    0.68
    principalColumn
    0.68
    
    0.66
     الرياضيه
    0.65
    ôgrafia
    0.65
    Have
    0.64
    Autoritní
    0.64
    Act Density 0.243%

    No Known Activations