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

    Neuronpedia

    INDEX
    Explanations

    content related to qualitative evaluations of conditions or items

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

    "always" or its synonyms

    np_acts-logits-general · gemini-2.0-flash

    not always necessarily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.71
     instead
    -0.61
    msgTypes
    -0.57
     rather
    -0.57
    instead
    -0.56
    rather
    -0.56
     basically
    -0.55
     سكانية
    -0.54
     plutôt
    -0.54
     نه
    -0.52
    POSITIVE LOGITS
     necessarily
    1.45
     necessariamente
    1.33
     necesariamente
    1.32
     nécessairement
    1.21
     forcément
    1.15
    necessarily
    1.14
     always
    1.10
    always
    1.02
     Always
    0.97
     همیشه
    0.96
    Act Density 0.533%

    No Known Activations