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

    Neuronpedia

    INDEX
    Explanations

    elements of secrecy and hidden emotions in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustos
    -0.17
    PTY
    -0.17
     voks
    -0.17
    .IContainer
    -0.16
    ANDOM
    -0.16
    loys
    -0.15
    ë²
    -0.15
    ÎķÎ¥
    -0.15
    ãĥ¬ãĥ¼
    -0.15
    tember
    -0.15
    POSITIVE LOGITS
     until
    0.20
     till
    0.16
     unless
    0.15
    upper
    0.15
     Pall
    0.15
    zm
    0.15
    641
    0.15
     Until
    0.14
    891
    0.14
     Buff
    0.14
    Act Density 0.111%

    No Known Activations