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

    Neuronpedia

    INDEX
    Explanations

    phrases related to invitations or announcements

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

    Followed by "you"

    np_acts-logits-general · gemini-2.0-flash

    questions and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CHAPITRE
    -0.90
     Theſe
    -0.74
     saites
    -0.74
     שוליים
    -0.73
    ​—
    -0.71
    født
    -0.70
     —,
    -0.69
     Efq
    -0.67
    —¿
    -0.66
     ――
    -0.65
    POSITIVE LOGITS
    info
    0.65
     можете
    0.63
     info
    0.62
     you
    0.59
     detailed
    0.58
     inform
    0.54
    You
    0.54
    you
    0.54
    detailed
    0.53
     informa
    0.52
    Act Density 0.096%

    No Known Activations