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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the concept of kindness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cher
    -0.17
    ç¼
    -0.16
    à¥Ģण
    -0.15
    ximo
    -0.15
    ánu
    -0.15
    çon
    -0.15
    ñana
    -0.15
    ional
    -0.15
    sse
    -0.15
    quia
    -0.14
    POSITIVE LOGITS
    red
    0.44
    erg
    0.36
    ergarten
    0.35
    ling
    0.34
    led
    0.34
    reds
    0.34
    gom
    0.32
    heart
    0.31
    -hearted
    0.28
    RED
    0.26
    Act Density 0.032%

    No Known Activations