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

    Neuronpedia

    INDEX
    Explanations

    terms related to reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emil
    -0.62
     weirdly
    -0.59
    zewod
    -0.57
    Autowired
    -0.57
    zieher
    -0.57
    divarius
    -0.57
    TemporalType
    -0.56
     виправивши
    -0.55
     kasarigan
    -0.55
    oarece
    -0.55
    POSITIVE LOGITS
     reputation
    3.27
     Reputation
    2.77
     reputations
    2.75
    Reputation
    2.49
     reputa
    2.19
     reputación
    2.12
     réputation
    2.03
     reput
    1.88
     repute
    1.64
    putation
    1.63
    Act Density 0.080%

    No Known Activations