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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to destruction and abandonment

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

    ceased to exist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miłość
    -0.33
    hæng
    -0.32
     karşı
    -0.32
    AutoScaleMode
    -0.31
     języka
    -0.30
     kı
    -0.30
     ζω
    -0.30
     textu
    -0.29
     Love
    -0.28
    ambil
    -0.28
    POSITIVE LOGITS
    rungsseite
    0.75
    帖最后由
    0.67
    rmtree
    0.59
     oprot
    0.56
    MessageOf
    0.56
    getMinutes
    0.56
    ſehen
    0.55
    DoubleQuotes
    0.54
    رشف
    0.54
     linkovi
    0.53
    Act Density 0.136%

    No Known Activations