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

    Neuronpedia

    INDEX
    Explanations

    prepositions, particularly the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.47
    Save
    -0.46
    ché
    -0.45
     Niki
    -0.45
    plus
    -0.44
    Plus
    -0.44
    ch
    -0.43
    code
    -0.43
    楠
    -0.43
    End
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.97
    varargin
    0.94
    DOCTYPE
    0.93
    migrationBuilder
    0.93
    AddTagHelper
    0.93
     EconPapers
    0.89
    EDEFAULT
    0.89
     mauva
    0.88
     fidé
    0.86
    SBATCH
    0.86
    Act Density 0.067%

    No Known Activations