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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating prior research or studies

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

    the phrase "Previous studies" or similar retrospective research references at the beginning of sentences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    當初
    -0.50
     defStyleAttr
    -0.49
     thereafter
    -0.47
     poffible
    -0.46
     itſelf
    -0.43
    IntoConstraints
    -0.43
    extAlignment
    -0.43
     potem
    -0.43
     бъде
    -0.42
     themſelves
    -0.42
    POSITIVE LOGITS
     successes
    0.52
     unsuccessful
    0.50
     års
    0.49
    หน้าน
    0.49
    Previous
    0.48
     attempts
    0.47
     successful
    0.47
     experience
    0.47
     Previous
    0.46
     versions
    0.45
    Act Density 0.257%

    No Known Activations