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

    Neuronpedia

    INDEX
    Explanations

    references to safety and secure environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.23
    aison
    -0.17
    inous
    -0.17
    idia
    -0.16
    ETERS
    -0.16
    loth
    -0.16
    sWith
    -0.15
    antino
    -0.15
    pers
    -0.15
    lage
    -0.15
    POSITIVE LOGITS
    -guard
    0.30
    keeping
    0.29
     haven
    0.27
     harbor
    0.27
     hav
    0.25
    AreaView
    0.25
     Haven
    0.25
     Harbor
    0.24
    (r
    0.24
     harb
    0.21
    Act Density 0.028%

    No Known Activations