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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "there."

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

    greetings and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.59
     mauva
    -0.56
    WebpackPlugin
    -0.53
     feroit
    -0.53
     kasarigan
    -0.52
     auroit
    -0.52
     matéri
    -0.51
    majánló
    -0.51
     Infór
    -0.50
     Infórmanos
    -0.50
    POSITIVE LOGITS
     there
    0.79
    there
    0.65
    Hiya
    0.57
     THERE
    0.55
     هناك
    0.55
     There
    0.50
    Heya
    0.47
    There
    0.47
    Hey
    0.43
     Hey
    0.43
    Act Density 0.003%

    No Known Activations