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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating user agreement or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pru
    -0.49
    tora
    -0.45
    Ự
    -0.44
     Điện
    -0.43
     surf
    -0.43
     heli
    -0.43
    she
    -0.42
     Tula
    -0.42
    BagLayout
    -0.42
    شن
    -0.42
    POSITIVE LOGITS
    expandindo
    1.24
     تضيفلها
    1.13
    tvguidetime
    0.94
     Administrativna
    0.93
     ComVisible
    0.92
     mergeFrom
    0.91
    AndEndTag
    0.89
    :+:
    0.89
    ########.
    0.87
    Aiheesta
    0.86
    Act Density 1.441%

    No Known Activations