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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and positive encouragement towards others

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

    "Hope you" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    hope you enjoy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apparently
    -0.93
     presumably
    -0.90
    apparently
    -0.86
    presumably
    -0.82
    probably
    -0.80
     probably
    -0.80
     basically
    -0.80
     praticamente
    -0.79
    almost
    -0.79
     practically
    -0.78
    POSITIVE LOGITS
     someday
    0.91
    DockStyle
    0.76
     soon
    0.73
     sớm
    0.73
     gelingt
    0.71
    ValueStyle
    0.70
     algún
    0.68
     Soon
    0.65
     succeeds
    0.64
     algun
    0.64
    Act Density 0.279%

    No Known Activations