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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we," indicating a focus on collective or group actions and perspectives

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

    Sentences starting with "We"

    np_acts-logits-general · gemini-2.0-flash

    "we" followed by common verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -1.06
    RectangleBorder
    -1.01
    extAlignment
    -1.01
    enumii
    -0.92
     ivelany
    -0.81
    DebuggerNonUser
    -0.79
    MLLoader
    -0.76
     MessageBoxIcon
    -0.75
    StoryboardSegue
    -0.74
    XmlAccessType
    -0.72
    POSITIVE LOGITS
     humans
    0.72
     all
    0.67
     mennesker
    0.56
     människor
    0.56
    We
    0.55
     us
    0.54
     semua
    0.53
     me
    0.51
     njego
    0.50
     inimes
    0.49
    Act Density 0.232%

    No Known Activations