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

    Neuronpedia

    INDEX
    Explanations

    the repeated usage of the word 'via'

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

    by means of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.60
     pleaſure
    -0.58
     itſelf
    -0.57
     myſelf
    -0.54
     ſtand
    -0.52
     themſelves
    -0.51
    ſelves
    -0.49
     ſtill
    -0.47
    ſelf
    -0.45
     enfans
    -0.45
    POSITIVE LOGITS
     via
    2.08
    Via
    1.71
     Via
    1.69
    via
    1.66
     VIA
    1.48
     vía
    1.35
    VIA
    1.26
     tramite
    1.24
     poprzez
    1.16
    vía
    1.09
    Act Density 0.018%

    No Known Activations