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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal relationships and allegations of infidelity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    refuse to delete comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.46
     pleaſure
    -0.46
    出版年
    -0.45
    findpost
    -0.45
     consultato
    -0.43
     faſt
    -0.43
     diſt
    -0.42
     ſta
    -0.41
    principalColumn
    -0.41
     ſever
    -0.41
    POSITIVE LOGITS
     heartbroken
    0.47
     remaja
    0.47
     kebenaran
    0.47
     meisje
    0.47
     Moraes
    0.46
     pemuda
    0.46
     screenshots
    0.45
     allegedly
    0.45
     Konsequ
    0.44
     morals
    0.44
    Act Density 0.019%

    No Known Activations