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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "hole" and its variations in various contexts

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

    hole / holes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sask
    -0.47
     Pozna
    -0.46
     kasarigan
    -0.46
     standard
    -0.46
     محفوظة
    -0.45
    nsito
    -0.45
    bibfield
    -0.44
    carpa
    -0.44
     paces
    -0.44
     Punjab
    -0.43
    POSITIVE LOGITS
    Hole
    1.24
    hole
    1.24
     HOLE
    1.20
     Hole
    1.18
     hole
    1.12
    HOLE
    1.11
    holes
    1.02
    Holes
    1.02
     Holes
    1.02
     holes
    1.00
    Act Density 0.008%

    No Known Activations