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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express emotional states or personal sentiments

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

    ends in y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    athione
    -0.60
    migrationBuilder
    -0.56
     препратки
    -0.55
    hilation
    -0.55
     nutella
    -0.54
     sterilization
    -0.53
     ampoule
    -0.53
    estination
    -0.51
     pleaſure
    -0.51
     UIApplication
    -0.50
    POSITIVE LOGITS
     Muddy
    0.57
     Shady
    0.56
     Sandy
    0.56
     Rocky
    0.56
    rocky
    0.55
    sandy
    0.55
     Windy
    0.54
    rafty
    0.54
    ffy
    0.54
     hairy
    0.53
    Act Density 0.036%

    No Known Activations