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

    Neuronpedia

    INDEX
    Explanations

    key terms associated with control and influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uards
    -0.14
    alara
    -0.14
    vince
    -0.14
     hoops
    -0.14
    ÄĻd
    -0.14
     yük
    -0.14
    yntax
    -0.14
     Buchanan
    -0.13
    nock
    -0.13
    edor
    -0.13
    POSITIVE LOGITS
     lag
    0.16
    unde
    0.15
     Miles
    0.15
    isha
    0.15
    gesch
    0.14
    658
    0.14
     DISCLAIMER
    0.14
     Poly
    0.14
     Princip
    0.14
    uet
    0.14
    Act Density 0.017%

    No Known Activations