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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reporting and rumors

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

    "reportedly"

    np_acts-logits-general · gemini-2.0-flash

    reportedly told

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.65
    -0.63
     myſelf
    -0.61
     Winaray
    -0.60
     itſelf
    -0.59
    󠁿
    -0.59
     ſche
    -0.58
    InputBorder
    -0.57
     RegExp
    -0.56
    RTLD
    -0.56
    POSITIVE LOGITS
     numerus
    0.40
     AssemblyCulture
    0.34
     negociaciones
    0.31
     gewöhnlich
    0.31
    brigens
    0.30
    __((
    0.30
     majeure
    0.29
     повіт
    0.29
    ValueStyle
    0.28
    šanās
    0.27
    Act Density 0.386%

    No Known Activations