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

    Neuronpedia

    INDEX
    Explanations

    instances of greetings and expressions of acknowledgment

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

    greetings and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.75
     nahilalakip
    -0.70
     esternos
    -0.66
    UserScript
    -0.66
    httphttps
    -0.65
     <<<<<<<<<<<<<<
    -0.65
     Infórmanos
    -0.63
     beginnetje
    -0.63
     ब्रेकडाउन
    -0.62
     propOrder
    -0.62
    POSITIVE LOGITS
    Hi
    0.40
     Sosial
    0.37
     Hello
    0.36
    Hey
    0.36
    Hello
    0.34
     Hi
    0.33
     Hey
    0.32
     réunion
    0.32
     Hallo
    0.32
     hello
    0.32
    Act Density 0.003%

    No Known Activations