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

    Neuronpedia

    INDEX
    Explanations

    the word "it" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the phrase "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dding
    -0.72
    package
    -0.66
    Asset
    -0.61
    Pad
    -0.60
    order
    -0.60
    Sword
    -0.59
    ban
    -0.58
     DW
    -0.57
     Expedition
    -0.56
     EE
    -0.55
    POSITIVE LOGITS
     relates
    1.31
     happens
    1.24
     stands
    1.23
     turns
    1.19
     unfolds
    1.13
     transpired
    1.09
     evolves
    1.01
     happened
    0.99
     unfolded
    0.97
     exists
    0.96
    Act Density 0.045%

    No Known Activations