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

    Neuronpedia

    INDEX
    Explanations

    phrases that express emotional sentiments and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fart
    -0.16
    iline
    -0.15
    quals
    -0.15
    boa
    -0.15
     Äijâu
    -0.14
     exactly
    -0.14
     bits
    -0.14
    uku
    -0.13
    asto
    -0.13
    OUNDS
    -0.13
    POSITIVE LOGITS
     those
    0.27
     Those
    0.24
    Those
    0.23
    those
    0.22
     ya
    0.21
    éĤ£äºĽ
    0.21
     cha
    0.18
     dem
    0.18
    CHA
    0.18
    cha
    0.17
    Act Density 0.458%

    No Known Activations