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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating upward movement or actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    winston
    -0.62
     Sint
    -0.61
    vertis
    -0.60
    Sint
    -0.58
    ellery
    -0.57
    Hô
    -0.57
     tic
    -0.56
     ent
    -0.55
     indeed
    -0.54
    tod
    -0.54
    POSITIVE LOGITS
     layui
    0.84
     GenerationType
    0.84
    цездатний
    0.83
    PreferredItem
    0.81
    NamedQueries
    0.80
    المناصب
    0.79
    }">
    0.77
     microfilm
    0.76
    alyptus
    0.75
    })$}
    0.73
    Act Density 0.016%

    No Known Activations