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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.63
     kasarigan
    -0.61
    قایناقلار
    -0.59
    AndEndTag
    -0.58
    cektir
    -0.58
     springfox
    -0.57
    SBATCH
    -0.57
    asteroide
    -0.56
     Peres
    -0.56
    ear
    -0.56
    POSITIVE LOGITS
     conceivably
    0.70
    Moi
    0.69
    ally
    0.68
    GeoNames
    0.65
     actually
    0.64
    ViewFeatures
    0.62
    lccc
    0.62
    ◀
    0.62
     même
    0.62
    ylle
    0.61
    Act Density 0.033%

    No Known Activations