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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate enumeration or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intrusion
    -0.86
     guiActiveUnfocused
    -0.62
    ans
    -0.60
     IPM
    -0.59
     affair
    -0.59
     Dragonbound
    -0.59
    NP
    -0.57
    existent
    -0.57
    matter
    -0.57
     deception
    -0.57
    POSITIVE LOGITS
     five
    0.80
     seven
    0.78
     excerpts
    0.77
     some
    0.76
     reasons
    0.76
     three
    0.75
     suggestions
    0.74
     six
    0.73
     nine
    0.72
     examples
    0.72
    Act Density 0.082%

    No Known Activations