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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and phrases indicating quantity or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æī¶
    -0.16
    bris
    -0.15
    .mas
    -0.15
    adera
    -0.15
     iconName
    -0.14
    ãĤĦãģĻ
    -0.14
    POCH
    -0.14
    åĢį
    -0.14
    ako
    -0.14
    trys
    -0.14
    POSITIVE LOGITS
     than
    0.30
    than
    0.22
    -than
    0.22
    _than
    0.19
     Than
    0.19
    iale
    0.17
     THAN
    0.17
    Than
    0.17
     niż
    0.16
     než
    0.15
    Act Density 0.205%

    No Known Activations