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

    Neuronpedia

    INDEX
    Explanations

    concepts related to thoughts and thinking processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.18
    elan
    -0.17
    eview
    -0.16
    erken
    -0.16
    oons
    -0.15
    haps
    -0.15
    aucoup
    -0.15
    ubbo
    -0.14
    iping
    -0.14
    nte
    -0.14
    POSITIVE LOGITS
    fulness
    0.21
    fully
    0.20
    lessly
    0.20
    avia
    0.15
    YTE
    0.15
    ека
    0.15
    soever
    0.14
    ERSHEY
    0.14
    /question
    0.14
    象
    0.14
    Act Density 0.032%

    No Known Activations