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

    Neuronpedia

    INDEX
    Explanations

    verbs that represent speech or writing actions

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

    reporting speech or writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.43
    şört
    -0.38
     Obrador
    -0.37
     Italijani
    -0.37
    HideFlags
    -0.35
    UAWEI
    -0.34
     betweenstory
    -0.34
    IntoConstraints
    -0.34
     Python
    -0.33
    újo
    -0.33
    POSITIVE LOGITS
     said
    0.89
    said
    0.73
    httphttps
    0.70
     SAID
    0.69
    enumi
    0.64
     Said
    0.63
     AssemblyTitle
    0.62
    richTextPanel
    0.62
    SequentialGroup
    0.59
    Said
    0.58
    Act Density 0.007%

    No Known Activations