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

    Neuronpedia

    INDEX
    Explanations

    references to apocalyptic themes and scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Apocalyptic or survival-related contexts

    np_acts-logits-general · gemini-2.0-flash

    apocalyptic Australian survival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.74
    󠁢
    -0.67
     فريبيس
    -0.66
     <<<<<<<<<<<<<<
    -0.66
    fjspx
    -0.61
    ágico
    -0.58
    InstanceState
    -0.58
     @"/
    -0.56
    Leod
    -0.56
    hyrchwyd
    -0.55
    POSITIVE LOGITS
     survival
    0.86
     survivors
    0.83
     Survival
    0.79
     survivor
    0.76
     survi
    0.74
     surviving
    0.72
     apocalypse
    0.70
    Survival
    0.69
    survival
    0.69
     survive
    0.68
    Act Density 0.217%

    No Known Activations