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

    Neuronpedia

    INDEX
    Explanations

    excessive or negative adjectives and phrases that indicate abundance or scarcity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ael
    -0.16
    isper
    -0.15
     ChÃŃ
    -0.14
    rong
    -0.14
    ust
    -0.14
    ansson
    -0.14
    onas
    -0.14
    LETE
    -0.14
    Exception
    -0.13
    uy
    -0.13
    POSITIVE LOGITS
     portions
    0.19
     portion
    0.18
    avo
    0.15
    \Id
    0.15
     sup
    0.15
    AFX
    0.14
     everyone
    0.14
    ubat
    0.14
    obody
    0.14
    ava
    0.14
    Act Density 0.222%

    No Known Activations