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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive associations or influences

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

    positively associated or correlated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ljiv
    -0.51
     Jenderal
    -0.47
     Suiza
    -0.47
     Escolar
    -0.46
     Ärz
    -0.43
     Pakai
    -0.42
     suyo
    -0.41
     meuble
    -0.41
     jäsen
    -0.40
     územ
    -0.40
    POSITIVE LOGITS
     positively
    1.89
     negatively
    1.51
     Posi
    1.18
     adversely
    1.02
    posi
    1.02
    Posi
    0.98
     favorably
    0.96
     favourably
    0.93
    RegressionTest
    0.70
     positiv
    0.69
    Act Density 0.008%

    No Known Activations