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

    Neuronpedia

    INDEX
    Explanations

    programming functions and variable manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    method calls with dot notation on objects.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     queſta
    -0.67
     Jefus
    -0.65
     automatiques
    -0.60
    AutoScale
    -0.60
    ("/:
    -0.58
    ('/:
    -0.57
     perfons
    -0.56
     للاسماء
    -0.56
     themſelves
    -0.54
    ("}\
    -0.54
    POSITIVE LOGITS
    (
    0.88
    ('
    0.59
    ("
    0.57
     (
    0.57
    (“
    0.52
    (‘
    0.51
    （
    0.47
    ((
    0.44
    ()
    0.44
    fortawesome
    0.44
    Act Density 0.226%

    No Known Activations