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

    Neuronpedia

    INDEX
    Explanations

    language related to compassion and empathy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledge
    -0.15
    loth
    -0.14
    ibo
    -0.14
    à¹Ģà¸Ńà¸ĩ
    -0.14
    ardon
    -0.14
    enda
    -0.14
    ÙĨØ´
    -0.14
    icari
    -0.14
    CISION
    -0.14
    orer
    -0.13
    POSITIVE LOGITS
     towards
    0.18
     toward
    0.17
    /em
    0.15
    compass
    0.15
    hod
    0.15
    ably
    0.15
    ately
    0.15
    itar
    0.14
    +xml
    0.14
    ively
    0.14
    Act Density 0.044%

    No Known Activations