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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements related to personal experiences and actions

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

    words followed by 'the' or 'to'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.53
     صوتيه
    -0.42
    KommentareTeilen
    -0.41
     juſ
    -0.40
    GEBURTSDATUM
    -0.38
    rungsseite
    -0.38
    AppCompatTheme
    -0.37
     Autorizaciones
    -0.36
     tranſ
    -0.36
    Архівовано
    -0.35
    POSITIVE LOGITS
    SequentialGroup
    0.56
    featureID
    0.46
     mellow
    0.46
     betweenstory
    0.45
    appreciated
    0.43
     Meksiku
    0.43
     moniker
    0.43
     Handsome
    0.42
     glistening
    0.41
     Rollo
    0.41
    Act Density 0.002%

    No Known Activations