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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to emotions and social sentiments, particularly around love and hate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    躇
    -0.88
    i
    -0.87
    lup
    -0.86
    pyplot
    -0.76
    в
    -0.74
    lines
    -0.73
     ‘
    -0.71
    âng
    -0.71
     “
    -0.70
    “……
    -0.70
    POSITIVE LOGITS
     وتسجيلات
    0.90
     Jefus
    0.89
    Gruss
    0.88
     ſhould
    0.88
     aveug
    0.87
    ...");
    0.86
     Heaton
    0.83
     fhould
    0.83
     caufe
    0.83
    paravant
    0.82
    Act Density 0.848%

    No Known Activations