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

    Neuronpedia

    INDEX
    Explanations

    greetings and farewell expressions in text

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

    greeting or hi there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ETZ
    -0.49
    Arach
    -0.48
     Packer
    -0.48
     tbe
    -0.46
    careous
    -0.45
     Courant
    -0.44
    tley
    -0.44
     ECA
    -0.44
     zar
    -0.43
     Wenger
    -0.43
    POSITIVE LOGITS
    Hi
    0.95
     Hi
    0.93
     ſta
    0.76
     hi
    0.75
     HI
    0.70
    hi
    0.69
    Hiya
    0.64
     Diſ
    0.63
     ainfi
    0.63
     ſte
    0.62
    Act Density 0.006%

    No Known Activations