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

    Neuronpedia

    INDEX
    Explanations

    terms related to unspoiled or untarnished concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.14
    bose
    -0.14
    quine
    -0.14
    aller
    -0.14
     缸
    -0.14
     Someone
    -0.14
    Someone
    -0.14
    .protobuf
    -0.14
    mlink
    -0.13
    glomer
    -0.13
    POSITIVE LOGITS
     gonna
    0.18
    nesty
    0.17
     Lim
    0.16
     zel
    0.16
     Drive
    0.15
    Lim
    0.15
     audio
    0.15
    arken
    0.14
    fried
    0.14
    ila
    0.14
    Act Density 0.000%

    No Known Activations