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

    Neuronpedia

    INDEX
    Explanations

    terms indicating relativity or comparative relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ory
    -0.19
    ORY
    -0.17
    nat
    -0.15
    hunter
    -0.15
    ermann
    -0.15
    ancial
    -0.15
    reme
    -0.14
     Hund
    -0.14
     Warren
    -0.14
     Schwarz
    -0.14
    POSITIVE LOGITS
     Barnett
    0.16
    857
    0.15
     relative
    0.15
    avou
    0.15
     humidity
    0.15
     Relative
    0.15
    gui
    0.15
    å¾ħ
    0.14
     fruit
    0.14
    itudes
    0.14
    Act Density 0.028%

    No Known Activations