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

    Neuronpedia

    INDEX
    Explanations

    requests for information and clarification on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _review
    -0.15
    itre
    -0.15
    _effects
    -0.14
    ignon
    -0.14
    ailable
    -0.14
    /effects
    -0.13
    plevel
    -0.13
    ме
    -0.13
    unami
    -0.13
    éĸ
    -0.13
    POSITIVE LOGITS
     answers
    0.34
     details
    0.32
     proof
    0.27
     concrete
    0.27
     confirmation
    0.27
     information
    0.25
     updates
    0.24
     answer
    0.24
     info
    0.24
     word
    0.23
    Act Density 0.192%

    No Known Activations