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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conditional statements and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.16
    ulatory
    -0.15
    jie
    -0.15
     bra
    -0.15
     हव
    -0.15
    actionDate
    -0.15
    âu
    -0.14
     distrib
    -0.14
    erver
    -0.14
    UNUSED
    -0.14
    POSITIVE LOGITS
    oucher
    0.15
    -eslint
    0.15
    357
    0.15
    olta
    0.15
    644
    0.15
    628
    0.14
    urdy
    0.14
    serialization
    0.14
    URT
    0.14
    SizeMode
    0.14
    Act Density 0.087%

    No Known Activations