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

    Neuronpedia

    INDEX
    Explanations

    common phrases that imply conditional situations or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alsy
    -0.16
    igers
    -0.16
    FRING
    -0.15
    ovy
    -0.15
    MESS
    -0.15
    /or
    -0.14
    igin
    -0.14
    iap
    -0.14
    inosaur
    -0.14
    ebek
    -0.14
    POSITIVE LOGITS
    oa
    0.16
     cro
    0.15
     polis
    0.15
    538
    0.14
    æī¬
    0.14
    leg
    0.14
    imum
    0.13
    heid
    0.13
    owa
    0.13
     بÛĮر
    0.13
    Act Density 0.130%

    No Known Activations