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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and safe practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acha
    -0.17
    AppState
    -0.15
    оÑĤов
    -0.15
    ÅĻÃŃd
    -0.15
    chia
    -0.15
    =edge
    -0.14
    ProgressHUD
    -0.14
    gs
    -0.14
    aison
    -0.14
    ieren
    -0.14
    POSITIVE LOGITS
     safe
    0.24
    .safe
    0.23
     Safe
    0.23
     haven
    0.22
     hav
    0.21
    safe
    0.21
     harbor
    0.20
     Haven
    0.19
     passage
    0.19
    .Safe
    0.19
    Act Density 0.020%

    No Known Activations