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

    Neuronpedia

    INDEX
    Explanations

    references to attendance at events or gatherings

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

    attended places or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.62
     protoimpl
    -0.58
     Diſ
    -0.57
     ſch
    -0.57
     ſche
    -0.53
     ſtate
    -0.51
     reaſon
    -0.50
     itſelf
    -0.49
     purpoſe
    -0.49
     reafon
    -0.49
    POSITIVE LOGITS
     attended
    1.66
    attended
    1.37
     Atten
    0.95
    Atten
    0.88
     unattended
    0.80
     visited
    0.78
     participated
    0.75
     Attend
    0.72
     Visited
    0.72
     Attending
    0.65
    Act Density 0.005%

    No Known Activations