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

    Neuronpedia

    INDEX
    Explanations

    complexity and relationships in scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.59
    CWE
    -0.53
    RTEX
    -0.53
     gynhyrchwyd
    -0.53
     للاسماء
    -0.52
    #+#
    -0.51
    SizeMode
    -0.50
     برانيه
    -0.50
    INSEE
    -0.49
    AddTagHelper
    -0.49
    POSITIVE LOGITS
     comment
    1.16
     comments
    1.08
     discussion
    0.90
     Comments
    0.86
     explanation
    0.85
     Comment
    0.85
     commented
    0.85
     COMMENTS
    0.84
     discusses
    0.84
     explained
    0.83
    Act Density 1.033%

    No Known Activations