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

    Neuronpedia

    INDEX
    Explanations

    references to the pronoun "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the pronoun "it"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    take it personally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.69
    MergeFrom
    -0.66
    الإنجليزية
    -0.65
     "..\..\
    -0.65
    ArrowToggle
    -0.62
    AccessorTable
    -0.61
    utnik
    -0.53
    askell
    -0.53
    URLException
    -0.51
    UnknownFieldSet
    -0.51
    POSITIVE LOGITS
     personally
    0.66
     upon
    0.65
     personal
    0.62
     personlig
    0.60
     osob
    0.56
    Upon
    0.53
     Upon
    0.52
     Personally
    0.52
     persönlich
    0.51
    ñones
    0.51
    Act Density 0.029%

    No Known Activations