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

    Neuronpedia

    INDEX
    Explanations

    instances of comparisons and contrasts in statements

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

    "Compared to" phrases

    np_acts-logits-general · gemini-2.0-flash

    compared to or with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.79
    WebElementEntity
    -0.78
     Chwiliwch
    -0.77
    thâu
    -0.75
     ExecuteAsync
    -0.74
    SharedDtor
    -0.73
    Népesség
    -0.71
     intStringLen
    -0.66
    enumi
    -0.65
    InSection
    -0.65
    POSITIVE LOGITS
     with
    0.57
     even
    0.55
     compared
    0.53
     perhaps
    0.51
    tymologie
    0.51
     what
    0.51
     con
    0.49
     comp
    0.47
    anet
    0.47
     bien
    0.46
    Act Density 0.083%

    No Known Activations