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

    Neuronpedia

    INDEX
    Explanations

    references to the present or current state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certain
    -1.50
    áĢ¯
    -1.50
     Wald
    -1.49
    particular
    -1.43
     xe
    -1.38
     nod
    -1.36
     Nad
    -1.35
    ingo
    -1.34
     prestigious
    -1.32
     qualified
    -1.30
    POSITIVE LOGITS
    Īĺ
    1.88
    ķ
    1.63
    pan
    1.62
    through
    1.60
    ¾
    1.57
     generation
    1.56
    ulence
    1.50
    RUPT
    1.47
     through
    1.46
    planes
    1.44
    Act Density 1.915%

    No Known Activations