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

    Neuronpedia

    INDEX
    Explanations

    terms related to vulnerable populations and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.17
    ponent
    -0.15
    άÏĥ
    -0.15
    aven
    -0.14
    atively
    -0.14
    /place
    -0.13
    ilan
    -0.13
    finity
    -0.13
    omitempty
    -0.13
    arine
    -0.13
    POSITIVE LOGITS
     individuals
    0.36
     persons
    0.32
     populations
    0.28
     population
    0.27
     person
    0.26
     citizens
    0.26
     souls
    0.25
     people
    0.24
     ones
    0.23
     Individuals
    0.21
    Act Density 0.247%

    No Known Activations