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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alto
    -0.15
    ÏĨι
    -0.14
    afc
    -0.14
    unci
    -0.14
    635
    -0.14
    afx
    -0.14
    оваÑĢ
    -0.14
    asa
    -0.14
    391
    -0.13
    uffs
    -0.13
    POSITIVE LOGITS
     certainly
    0.21
     even
    0.19
     also
    0.18
    çĶļèĩ³
    0.17
     dokonce
    0.16
    dit
    0.15
    ä¹Łä¸į
    0.15
     pedig
    0.15
    亦
    0.15
    ãģłãģ£ãģ¦
    0.15
    Act Density 0.370%

    No Known Activations