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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the loss of compatibility or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²
    -1.87
    lement
    -1.78
    ¾
    -1.78
    Į
    -1.70
    -1.69
    Īĺ
    -1.69
    ns
    -1.66
    lements
    -1.64
    ³
    -1.62
    ¤
    -1.60
    POSITIVE LOGITS
     Apollo
    1.45
     Done
    1.44
    lux
    1.39
    adoc
    1.37
    rake
    1.37
    googleapis
    1.35
     Mars
    1.35
    rub
    1.35
    Simplify
    1.33
    golang
    1.33
    Act Density 0.260%

    No Known Activations