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

    Neuronpedia

    INDEX
    Explanations

    elements of social interactions and their emotional undercurrents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .inflate
    -0.18
    MBED
    -0.16
     Loose
    -0.14
    Ø´ÙĪ
    -0.14
     loos
    -0.13
     lö
    -0.13
    eos
    -0.13
    :///
    -0.13
    λοÏħ
    -0.13
    eo
    -0.13
    POSITIVE LOGITS
     silent
    0.84
     silence
    0.83
     quiet
    0.77
    silent
    0.72
     Silent
    0.69
     Silence
    0.68
    quiet
    0.60
     Quiet
    0.60
    Quiet
    0.57
     quieter
    0.56
    Act Density 0.309%

    No Known Activations