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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and positive feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oÄį
    -0.14
    éĢĢ
    -0.14
    ä¼Ĺ
    -0.13
    INE
    -0.13
    اØŃ
    -0.13
    çľ¾
    -0.13
    boro
    -0.13
     rip
    -0.13
    rick
    -0.13
    asin
    -0.13
    POSITIVE LOGITS
    celik
    0.18
    .swt
    0.17
    ardu
    0.16
     Colony
    0.15
    jad
    0.14
    yar
    0.14
    poke
    0.14
     slic
    0.14
    porter
    0.14
    .AutoComplete
    0.14
    Act Density 0.067%

    No Known Activations