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

    Neuronpedia

    INDEX
    Explanations

    mentions of research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.73
    помним
    -0.66
    لیس
    -0.66
    NewUrlParser
    -0.66
    rawan
    -0.64
    ότε
    -0.61
    ']")
    -0.60
     censiti
    -0.57
    >{@
    -0.56
    LookAnd
    -0.55
    POSITIVE LOGITS
     paper
    0.90
     Paper
    0.82
     Deliver
    0.79
    Paper
    0.72
     deliver
    0.72
    deliver
    0.71
    paper
    0.70
    Deliver
    0.70
     delivered
    0.69
     PAPER
    0.68
    Act Density 0.142%

    No Known Activations