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

    Neuronpedia

    INDEX
    Explanations

    phrases that mention "some" or refer to uncertain quantities

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

    Following "some"

    np_acts-logits-general · gemini-2.0-flash

    some [noun phrase]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     any
    -0.78
    any
    -0.62
     quaisquer
    -0.60
     Any
    -0.60
    Any
    -0.59
     <<<<<<<<<<<<<<
    -0.57
     żad
    -0.56
    seamnă
    -0.56
     cualquier
    -0.54
    DataPropertyName
    -0.54
    POSITIVE LOGITS
     sort
    1.25
    things
    1.06
     kind
    1.00
    sort
    0.93
    thig
    0.93
     degree
    0.93
    ones
    0.88
     semblance
    0.87
    bodies
    0.86
     Sort
    0.82
    Act Density 0.147%

    No Known Activations