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

    Neuronpedia

    INDEX
    Explanations

    references to physical openings or gaps in objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIA
    -0.15
    oha
    -0.14
    iment
    -0.14
    /mat
    -0.14
    otec
    -0.14
    ut
    -0.14
    Globals
    -0.14
    å·»
    -0.14
     firma
    -0.14
     Werner
    -0.13
    POSITIVE LOGITS
     holes
    0.23
    holes
    0.22
    hole
    0.21
     hole
    0.21
    -hole
    0.20
     Hole
    0.19
    -mouth
    0.19
    ç©´
    0.19
     bored
    0.19
    rico
    0.16
    Act Density 0.091%

    No Known Activations