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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe optimal methods or approaches to various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARAM
    -0.15
    cip
    -0.15
    dum
    -0.14
    llib
    -0.14
    Toast
    -0.14
    arl
    -0.14
    .rd
    -0.14
    幸
    -0.14
    andaÅŁ
    -0.14
    ëł
    -0.14
    POSITIVE LOGITS
    ija
    0.18
    ow
    0.17
    owe
    0.15
    stell
    0.15
     advice
    0.15
    bl
    0.15
     Eag
    0.15
    urge
    0.14
    1
    0.14
    st
    0.14
    Act Density 0.069%

    No Known Activations