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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical specifications and implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     мәкал
    -0.62
     للاسماء
    -0.59
    +#+#
    -0.59
     INTERESAR
    -0.54
    twimg
    -0.53
    OGND
    -0.53
    msgTypes
    -0.51
    :✨
    -0.51
     GenerationType
    -0.51
     resourceCulture
    -0.50
    POSITIVE LOGITS
    <strong>
    1.15
    <b>
    1.08
    <i>
    0.66
    <em>
    0.65
    <u>
    0.57
    <code>
    0.52
    <s>
    0.43
     
    0.41
     kanssa
    0.39
     avulla
    0.36
    Act Density 0.840%

    No Known Activations