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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing duration or continuity

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

    "long as"

    np_acts-logits-general · gemini-2.0-flash

    long as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.89
    ValueStyle
    -0.84
     Numerade
    -0.83
    IUrlHelper
    -0.80
     autorytatywna
    -0.75
    สือ
    -0.73
    DebuggerStep
    -0.72
     Савезне
    -0.70
     myſelf
    -0.70
    Datuak
    -0.70
    POSITIVE LOGITS
    glie
    0.61
     they
    0.53
     alive
    0.52
    XDECREF
    0.50
     remember
    0.50
     pamię
    0.50
     there
    0.48
     we
    0.47
    TagHelper
    0.47
     keep
    0.47
    Act Density 0.058%

    No Known Activations