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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to technical or software functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.60
    if
    -0.56
    ara
    -0.52
    ar
    -0.51
    na
    -0.51
    ",
    -0.50
    oni
    -0.50
    ot
    -0.49
    oro
    -0.49
    ra
    -0.48
    POSITIVE LOGITS
     мәкал
    1.08
    1.00
    dafx
    0.96
     Савезне
    0.90
    <bos>
    0.89
    etheless
    0.86
    Enllaces
    0.86
    drawal
    0.84
    StreetMap
    0.82
    EndContext
    0.81
    Act Density 2.184%

    No Known Activations