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

    Neuronpedia

    INDEX
    Explanations

    references to global situations and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fty
    -0.70
    elta
    -0.66
    eus
    -0.61
    ulo
    -0.61
    apult
    -0.60
    eln
    -0.60
    !/
    -0.60
    crow
    -0.60
     Squadron
    -0.59
    Forward
    -0.59
    POSITIVE LOGITS
    where
    0.88
    idents
    0.80
     where
    0.76
     meanwhile
    0.72
     mainland
    0.71
     populous
    0.69
     alike
    0.68
     Asians
    0.67
     populations
    0.67
     majorities
    0.67
    Act Density 0.119%

    No Known Activations