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

    Neuronpedia

    INDEX
    Explanations

    frequent verbs and their forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulnerability
    -0.20
     Vulner
    -0.18
     vulner
    -0.18
     vulnerable
    -0.17
    625
    -0.16
     Cities
    -0.15
    487
    -0.14
    rey
    -0.14
    utr
    -0.14
     Exposure
    -0.13
    POSITIVE LOGITS
     unrelated
    0.19
     Laurie
    0.15
    pirit
    0.15
    losion
    0.15
    .TryParse
    0.15
    prit
    0.14
     traff
    0.14
    ügen
    0.14
    oric
    0.14
    zione
    0.14
    Act Density 0.002%

    No Known Activations