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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and attraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unts
    -0.15
     bargain
    -0.15
    angan
    -0.15
     Anti
    -0.14
    èĻİ
    -0.14
     miêu
    -0.14
    elles
    -0.14
    embre
    -0.14
    rescia
    -0.14
    cke
    -0.14
    POSITIVE LOGITS
    çģ¯
    0.15
    rez
    0.14
     *)((
    0.14
    ìłĢ
    0.14
    iete
    0.14
    ãģ»ãģ©
    0.13
    okol
    0.13
    orz
    0.13
     Lifetime
    0.13
    stitute
    0.13
    Act Density 0.128%

    No Known Activations