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

    Neuronpedia

    INDEX
    Explanations

    references to safe spaces and supportive environments for victims of violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lode
    -0.54
     Eind
    -0.53
    adə
    -0.53
    benhavn
    -0.51
    ctools
    -0.51
    Eind
    -0.50
    Wildcard
    -0.48
    ruhe
    -0.48
    kosti
    -0.48
    ginald
    -0.47
    POSITIVE LOGITS
     outdoors
    0.76
     outdoor
    0.63
    TintMode
    0.59
     someplace
    0.58
     خارج
    0.56
     تضيفلها
    0.56
     secluded
    0.55
     Outdoors
    0.54
     outside
    0.54
     indoors
    0.54
    Act Density 0.338%

    No Known Activations